├── .github └── workflows │ └── ci.yml ├── .gitignore ├── .gitmodules ├── .pre-commit-config.yaml ├── LICENSE ├── README.md ├── assets └── images │ ├── versa-dark-char.png │ ├── versa-dark.png │ ├── versa-light-char.png │ └── versa-light.png ├── ci └── python_check.yaml ├── demo ├── arecho_config.yaml ├── arecho_results.json ├── chunked_results.json ├── chunked_results.json.chunks │ └── pred │ │ ├── long_test.wav_chunk0000_0.000-2.000.wav │ │ ├── long_test.wav_chunk0001_1.000-3.000.wav │ │ ├── long_test.wav_chunk0002_2.000-4.000.wav │ │ ├── long_test.wav_chunk0003_3.000-5.000.wav │ │ ├── long_test.wav_chunk0004_4.000-6.000.wav │ │ ├── long_test.wav_chunk0005_5.000-7.000.wav │ │ ├── long_test.wav_chunk0006_6.000-8.000.wav │ │ ├── long_test.wav_chunk0007_7.000-9.000.wav │ │ ├── long_test.wav_chunk0008_8.000-10.000.wav │ │ └── long_test.wav_chunk0009_9.000-10.000.wav ├── hub │ └── f2d5200177fd6a33b278b7b76b454f25cd8ee866d55c122e69fccf6c7467d37d.wavlm_large.pt.lock ├── interpreter_config.yaml ├── long_audio_demo │ └── long_test.wav ├── metrics_analysis.csv ├── metrics_tree.csv ├── scores.scp ├── sunburst_chart.html ├── traditional_cpu_results.json ├── universa_audioref_config.yaml ├── universa_audioref_results.json ├── universa_noref_config.yaml ├── universa_noref_results.json ├── versa_demo_interspeech2024.ipynb └── versa_v2_demo.ipynb ├── docs ├── ci.md ├── contributing.md ├── supported_metrics.md ├── users.md └── visualization.md ├── egs ├── demo │ ├── codec.yaml │ ├── se.yaml │ ├── svs.yaml │ └── tts.yaml ├── external_install_need.yaml ├── general.yaml ├── interpreter.yaml ├── run_cpu.sh ├── run_gpu.sh ├── separate_metrics │ ├── arecho.yaml │ ├── asr_match.yaml │ ├── asvspoof.yaml │ ├── audiobox_aesthetics.yaml │ ├── discrete_speech.yaml │ ├── emo_similarity.yaml │ ├── fad.yaml │ ├── kid.yaml │ ├── lid.yaml │ ├── mcd_f0.yaml │ ├── nisqa.yaml │ ├── nomad.yaml │ ├── noresqa.yaml │ ├── pam.yaml │ ├── pesq_stoi.yaml │ ├── pseudo_mos.yaml │ ├── pysepm.yaml │ ├── qwen2_audio.yaml │ ├── scoreq.yaml │ ├── se_snr.yaml │ ├── sheet_ssqa.yaml │ ├── sigmos.yaml │ ├── snr_related.yaml │ ├── speaking_rate.yaml │ ├── spk_similarity.yaml │ ├── squim.yaml │ ├── srmr.yaml │ ├── universa.yaml │ ├── utmos2.yaml │ ├── vad.yaml │ ├── visqol.yaml │ ├── vqscore.yaml │ ├── w2v2_dimensional_emotion.yaml │ ├── warpq.yaml │ ├── wer.yaml │ ├── wer_english.yaml │ └── wvmos.yaml ├── singing.yaml ├── speech.yaml ├── speech_cpu.yaml ├── speech_gpu.yaml ├── survey │ ├── configs │ │ └── speech.yaml │ ├── run_general.sh │ └── run_speech.sh └── universa_prepare │ ├── cpu_subset.yaml │ ├── gpu_subset.yaml │ └── universa_prepare.yaml ├── launch_local.sh ├── launch_slurm.sh ├── pyproject.toml ├── scripts ├── chunk_func │ └── chunk.py ├── description │ ├── README.md │ ├── interpreter.py │ ├── interpreter_shared.py │ └── text_llm_description.py ├── extract_key.py ├── postprocess │ ├── check_llm_result_match.py │ ├── filter_wer.py │ ├── post_process.sh │ ├── qwen2_audio_json_output_standardizer.py │ ├── qwen2_audio_json_output_standardizer_batch.py │ ├── qwen2_audio_json_output_standardizer_eg.py │ └── qwen2_audio_jsonl_standardizer_batch.py ├── preprocess │ ├── dir2scp.py │ ├── dir2scp.sh │ └── jsonl2scp.py ├── show_result.py ├── survey │ ├── average_result.py │ ├── get_wer.py │ ├── prepare_audioset-test.py │ ├── prepare_librispeech-test-clean.py │ └── prepare_musdb.py └── visualization │ ├── README.md │ ├── build_metricsTree.py │ ├── radar_chart.png │ ├── radar_chart.py │ ├── requirements.txt │ ├── sample_sunburstchart.png │ └── sunburst_chart.py ├── setup.cfg ├── setup.py ├── test ├── test_general.py ├── test_metrics │ ├── test_asr_matching.py │ ├── test_cdpam.py │ ├── test_discrete_speech.py │ ├── test_dnsmos_pro.py │ ├── test_dpam.py │ ├── test_emo_vad.py │ └── test_stoi.py ├── test_pipeline │ ├── test_asr_match.py │ ├── test_asvspoof.py │ ├── test_audiobox_aesthetics.py │ ├── test_emo_similarity.py │ ├── test_fad.py │ ├── test_general.py │ ├── test_lid.py │ ├── test_nisqa.py │ ├── test_nomad.py │ ├── test_noresqa.py │ ├── test_pam.py │ ├── test_pysepm.py │ ├── test_qwen2_audio.py │ ├── test_scoreq.py │ ├── test_sigmos.py │ ├── test_speaking_rate.py │ ├── test_srmr.py │ ├── test_utmosv2.py │ ├── test_vad.py │ ├── test_vqscore.py │ ├── test_warpq.py │ ├── test_wer.py │ └── test_wvmos.py └── test_samples │ ├── test1.scp │ ├── test1 │ └── test.wav │ ├── test2.scp │ ├── test2 │ └── test.wav │ ├── test_result.txt │ └── text ├── todo.txt ├── tools ├── activate_utmosv2.sh ├── easy_install.sh ├── install_asvspoof.sh ├── install_audiobox-aesthetics.sh ├── install_emo2vec.sh ├── install_fadtk.sh ├── install_fairseq.sh ├── install_gitlfs.md ├── install_nomad.sh ├── install_noresqa.sh ├── install_pyannote.sh ├── install_pysepm.sh ├── install_scoreq.sh ├── install_srmr.sh ├── install_ssl-singer-identity.sh ├── install_utmosv2.sh ├── install_visqol.md ├── install_warpq.sh ├── install_wvmos.sh ├── pysepm │ └── pysepm │ │ └── intelligibilityMeasures.py └── setup_nisqa.sh └── versa ├── __init__.py ├── bin ├── __init__.py ├── aggregate_results.py ├── scorer.py └── scorer_chunk.py ├── corpus_metrics ├── __init__.py ├── clap_score.py ├── espnet_wer.py ├── fad.py ├── individual_fad.py ├── kid.py ├── owsm_wer.py ├── test └── whisper_wer.py ├── metrics.py ├── scorer_shared.py ├── sequence_metrics ├── __init__.py ├── mcd_f0.py ├── signal_metric.py └── warpq.py ├── utils_shared.py └── utterance_metrics ├── __init__.py ├── arecho.py ├── asr_matching.py ├── asvspoof_score.py ├── audiobox_aesthetics_score.py ├── cdpam_distance.py ├── chroma_alignment.py ├── discrete_speech.py ├── dpam_distance.py ├── emo_vad.py ├── emotion.py ├── log_wmse.py ├── nisqa.py ├── nisqa_utils ├── __init__.py └── nisqa_lib.py ├── nomad.py ├── noresqa.py ├── owsm_lid.py ├── pam.py ├── pam_utils └── clap.py ├── pesq_score.py ├── pseudo_mos.py ├── pysepm.py ├── qwen2_audio.py ├── qwen_omni.py ├── scoreq.py ├── se_snr.py ├── sheet_ssqa.py ├── sigmos.py ├── singer.py ├── speaker.py ├── speaking_rate.py ├── squim.py ├── srmr.py ├── stoi.py ├── universa.py ├── vad.py ├── visqol_score.py ├── vqscore.py └── wvmos.py /.github/workflows/ci.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/.github/workflows/ci.yml -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/.gitignore -------------------------------------------------------------------------------- /.gitmodules: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/.gitmodules -------------------------------------------------------------------------------- /.pre-commit-config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/.pre-commit-config.yaml -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/README.md -------------------------------------------------------------------------------- /assets/images/versa-dark-char.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/assets/images/versa-dark-char.png -------------------------------------------------------------------------------- /assets/images/versa-dark.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/assets/images/versa-dark.png -------------------------------------------------------------------------------- /assets/images/versa-light-char.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/assets/images/versa-light-char.png -------------------------------------------------------------------------------- /assets/images/versa-light.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/assets/images/versa-light.png -------------------------------------------------------------------------------- /ci/python_check.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/ci/python_check.yaml -------------------------------------------------------------------------------- /demo/arecho_config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/demo/arecho_config.yaml -------------------------------------------------------------------------------- /demo/arecho_results.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/demo/arecho_results.json -------------------------------------------------------------------------------- /demo/chunked_results.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/demo/chunked_results.json -------------------------------------------------------------------------------- /demo/chunked_results.json.chunks/pred/long_test.wav_chunk0000_0.000-2.000.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/demo/chunked_results.json.chunks/pred/long_test.wav_chunk0000_0.000-2.000.wav -------------------------------------------------------------------------------- /demo/chunked_results.json.chunks/pred/long_test.wav_chunk0001_1.000-3.000.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/demo/chunked_results.json.chunks/pred/long_test.wav_chunk0001_1.000-3.000.wav -------------------------------------------------------------------------------- /demo/chunked_results.json.chunks/pred/long_test.wav_chunk0002_2.000-4.000.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/demo/chunked_results.json.chunks/pred/long_test.wav_chunk0002_2.000-4.000.wav -------------------------------------------------------------------------------- /demo/chunked_results.json.chunks/pred/long_test.wav_chunk0003_3.000-5.000.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/demo/chunked_results.json.chunks/pred/long_test.wav_chunk0003_3.000-5.000.wav -------------------------------------------------------------------------------- /demo/chunked_results.json.chunks/pred/long_test.wav_chunk0004_4.000-6.000.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/demo/chunked_results.json.chunks/pred/long_test.wav_chunk0004_4.000-6.000.wav -------------------------------------------------------------------------------- /demo/chunked_results.json.chunks/pred/long_test.wav_chunk0005_5.000-7.000.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/demo/chunked_results.json.chunks/pred/long_test.wav_chunk0005_5.000-7.000.wav -------------------------------------------------------------------------------- /demo/chunked_results.json.chunks/pred/long_test.wav_chunk0006_6.000-8.000.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/demo/chunked_results.json.chunks/pred/long_test.wav_chunk0006_6.000-8.000.wav -------------------------------------------------------------------------------- /demo/chunked_results.json.chunks/pred/long_test.wav_chunk0007_7.000-9.000.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/demo/chunked_results.json.chunks/pred/long_test.wav_chunk0007_7.000-9.000.wav -------------------------------------------------------------------------------- /demo/chunked_results.json.chunks/pred/long_test.wav_chunk0008_8.000-10.000.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/demo/chunked_results.json.chunks/pred/long_test.wav_chunk0008_8.000-10.000.wav -------------------------------------------------------------------------------- /demo/chunked_results.json.chunks/pred/long_test.wav_chunk0009_9.000-10.000.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/demo/chunked_results.json.chunks/pred/long_test.wav_chunk0009_9.000-10.000.wav -------------------------------------------------------------------------------- /demo/hub/f2d5200177fd6a33b278b7b76b454f25cd8ee866d55c122e69fccf6c7467d37d.wavlm_large.pt.lock: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /demo/interpreter_config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/demo/interpreter_config.yaml -------------------------------------------------------------------------------- /demo/long_audio_demo/long_test.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/demo/long_audio_demo/long_test.wav -------------------------------------------------------------------------------- /demo/metrics_analysis.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/demo/metrics_analysis.csv -------------------------------------------------------------------------------- /demo/metrics_tree.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/demo/metrics_tree.csv -------------------------------------------------------------------------------- /demo/scores.scp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/demo/scores.scp -------------------------------------------------------------------------------- /demo/sunburst_chart.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/demo/sunburst_chart.html -------------------------------------------------------------------------------- /demo/traditional_cpu_results.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/demo/traditional_cpu_results.json -------------------------------------------------------------------------------- /demo/universa_audioref_config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/demo/universa_audioref_config.yaml -------------------------------------------------------------------------------- /demo/universa_audioref_results.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/demo/universa_audioref_results.json -------------------------------------------------------------------------------- /demo/universa_noref_config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/demo/universa_noref_config.yaml -------------------------------------------------------------------------------- /demo/universa_noref_results.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/demo/universa_noref_results.json -------------------------------------------------------------------------------- /demo/versa_demo_interspeech2024.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/demo/versa_demo_interspeech2024.ipynb -------------------------------------------------------------------------------- /demo/versa_v2_demo.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/demo/versa_v2_demo.ipynb -------------------------------------------------------------------------------- /docs/ci.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/docs/ci.md -------------------------------------------------------------------------------- /docs/contributing.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/docs/contributing.md -------------------------------------------------------------------------------- /docs/supported_metrics.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/docs/supported_metrics.md -------------------------------------------------------------------------------- /docs/users.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/docs/users.md -------------------------------------------------------------------------------- /docs/visualization.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/docs/visualization.md -------------------------------------------------------------------------------- /egs/demo/codec.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/egs/demo/codec.yaml -------------------------------------------------------------------------------- /egs/demo/se.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/egs/demo/se.yaml -------------------------------------------------------------------------------- /egs/demo/svs.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/egs/demo/svs.yaml -------------------------------------------------------------------------------- /egs/demo/tts.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/egs/demo/tts.yaml -------------------------------------------------------------------------------- /egs/external_install_need.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/egs/external_install_need.yaml -------------------------------------------------------------------------------- /egs/general.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/egs/general.yaml -------------------------------------------------------------------------------- /egs/interpreter.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/egs/interpreter.yaml -------------------------------------------------------------------------------- /egs/run_cpu.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/egs/run_cpu.sh -------------------------------------------------------------------------------- /egs/run_gpu.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/egs/run_gpu.sh -------------------------------------------------------------------------------- /egs/separate_metrics/arecho.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/egs/separate_metrics/arecho.yaml -------------------------------------------------------------------------------- /egs/separate_metrics/asr_match.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/egs/separate_metrics/asr_match.yaml -------------------------------------------------------------------------------- /egs/separate_metrics/asvspoof.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/egs/separate_metrics/asvspoof.yaml -------------------------------------------------------------------------------- /egs/separate_metrics/audiobox_aesthetics.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/egs/separate_metrics/audiobox_aesthetics.yaml -------------------------------------------------------------------------------- /egs/separate_metrics/discrete_speech.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/egs/separate_metrics/discrete_speech.yaml -------------------------------------------------------------------------------- /egs/separate_metrics/emo_similarity.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/egs/separate_metrics/emo_similarity.yaml -------------------------------------------------------------------------------- /egs/separate_metrics/fad.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/egs/separate_metrics/fad.yaml -------------------------------------------------------------------------------- /egs/separate_metrics/kid.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/egs/separate_metrics/kid.yaml -------------------------------------------------------------------------------- /egs/separate_metrics/lid.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/egs/separate_metrics/lid.yaml -------------------------------------------------------------------------------- /egs/separate_metrics/mcd_f0.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/egs/separate_metrics/mcd_f0.yaml -------------------------------------------------------------------------------- /egs/separate_metrics/nisqa.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/egs/separate_metrics/nisqa.yaml -------------------------------------------------------------------------------- /egs/separate_metrics/nomad.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/egs/separate_metrics/nomad.yaml -------------------------------------------------------------------------------- /egs/separate_metrics/noresqa.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/egs/separate_metrics/noresqa.yaml -------------------------------------------------------------------------------- /egs/separate_metrics/pam.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/egs/separate_metrics/pam.yaml -------------------------------------------------------------------------------- /egs/separate_metrics/pesq_stoi.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/egs/separate_metrics/pesq_stoi.yaml -------------------------------------------------------------------------------- /egs/separate_metrics/pseudo_mos.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/egs/separate_metrics/pseudo_mos.yaml -------------------------------------------------------------------------------- /egs/separate_metrics/pysepm.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/egs/separate_metrics/pysepm.yaml -------------------------------------------------------------------------------- /egs/separate_metrics/qwen2_audio.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/egs/separate_metrics/qwen2_audio.yaml -------------------------------------------------------------------------------- /egs/separate_metrics/scoreq.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/egs/separate_metrics/scoreq.yaml -------------------------------------------------------------------------------- /egs/separate_metrics/se_snr.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/egs/separate_metrics/se_snr.yaml -------------------------------------------------------------------------------- /egs/separate_metrics/sheet_ssqa.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/egs/separate_metrics/sheet_ssqa.yaml -------------------------------------------------------------------------------- /egs/separate_metrics/sigmos.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/egs/separate_metrics/sigmos.yaml -------------------------------------------------------------------------------- /egs/separate_metrics/snr_related.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/egs/separate_metrics/snr_related.yaml -------------------------------------------------------------------------------- /egs/separate_metrics/speaking_rate.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/egs/separate_metrics/speaking_rate.yaml -------------------------------------------------------------------------------- /egs/separate_metrics/spk_similarity.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/egs/separate_metrics/spk_similarity.yaml -------------------------------------------------------------------------------- /egs/separate_metrics/squim.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/egs/separate_metrics/squim.yaml -------------------------------------------------------------------------------- /egs/separate_metrics/srmr.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/egs/separate_metrics/srmr.yaml -------------------------------------------------------------------------------- /egs/separate_metrics/universa.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/egs/separate_metrics/universa.yaml -------------------------------------------------------------------------------- /egs/separate_metrics/utmos2.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/egs/separate_metrics/utmos2.yaml -------------------------------------------------------------------------------- /egs/separate_metrics/vad.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/egs/separate_metrics/vad.yaml -------------------------------------------------------------------------------- /egs/separate_metrics/visqol.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/egs/separate_metrics/visqol.yaml -------------------------------------------------------------------------------- /egs/separate_metrics/vqscore.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/egs/separate_metrics/vqscore.yaml -------------------------------------------------------------------------------- /egs/separate_metrics/w2v2_dimensional_emotion.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/egs/separate_metrics/w2v2_dimensional_emotion.yaml -------------------------------------------------------------------------------- /egs/separate_metrics/warpq.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/egs/separate_metrics/warpq.yaml -------------------------------------------------------------------------------- /egs/separate_metrics/wer.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/egs/separate_metrics/wer.yaml -------------------------------------------------------------------------------- /egs/separate_metrics/wer_english.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/egs/separate_metrics/wer_english.yaml -------------------------------------------------------------------------------- /egs/separate_metrics/wvmos.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/egs/separate_metrics/wvmos.yaml -------------------------------------------------------------------------------- /egs/singing.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/egs/singing.yaml -------------------------------------------------------------------------------- /egs/speech.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/egs/speech.yaml -------------------------------------------------------------------------------- /egs/speech_cpu.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/egs/speech_cpu.yaml -------------------------------------------------------------------------------- /egs/speech_gpu.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/egs/speech_gpu.yaml -------------------------------------------------------------------------------- /egs/survey/configs/speech.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/egs/survey/configs/speech.yaml -------------------------------------------------------------------------------- /egs/survey/run_general.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/egs/survey/run_general.sh -------------------------------------------------------------------------------- /egs/survey/run_speech.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/egs/survey/run_speech.sh -------------------------------------------------------------------------------- /egs/universa_prepare/cpu_subset.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/egs/universa_prepare/cpu_subset.yaml -------------------------------------------------------------------------------- /egs/universa_prepare/gpu_subset.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/egs/universa_prepare/gpu_subset.yaml -------------------------------------------------------------------------------- /egs/universa_prepare/universa_prepare.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/egs/universa_prepare/universa_prepare.yaml -------------------------------------------------------------------------------- /launch_local.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/launch_local.sh -------------------------------------------------------------------------------- /launch_slurm.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/launch_slurm.sh -------------------------------------------------------------------------------- /pyproject.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/pyproject.toml -------------------------------------------------------------------------------- /scripts/chunk_func/chunk.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/scripts/chunk_func/chunk.py -------------------------------------------------------------------------------- /scripts/description/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/scripts/description/README.md -------------------------------------------------------------------------------- /scripts/description/interpreter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/scripts/description/interpreter.py -------------------------------------------------------------------------------- /scripts/description/interpreter_shared.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/scripts/description/interpreter_shared.py -------------------------------------------------------------------------------- /scripts/description/text_llm_description.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/scripts/description/text_llm_description.py -------------------------------------------------------------------------------- /scripts/extract_key.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/scripts/extract_key.py -------------------------------------------------------------------------------- /scripts/postprocess/check_llm_result_match.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/scripts/postprocess/check_llm_result_match.py -------------------------------------------------------------------------------- /scripts/postprocess/filter_wer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/scripts/postprocess/filter_wer.py -------------------------------------------------------------------------------- /scripts/postprocess/post_process.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/scripts/postprocess/post_process.sh -------------------------------------------------------------------------------- /scripts/postprocess/qwen2_audio_json_output_standardizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/scripts/postprocess/qwen2_audio_json_output_standardizer.py -------------------------------------------------------------------------------- /scripts/postprocess/qwen2_audio_json_output_standardizer_batch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/scripts/postprocess/qwen2_audio_json_output_standardizer_batch.py -------------------------------------------------------------------------------- /scripts/postprocess/qwen2_audio_json_output_standardizer_eg.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/scripts/postprocess/qwen2_audio_json_output_standardizer_eg.py -------------------------------------------------------------------------------- /scripts/postprocess/qwen2_audio_jsonl_standardizer_batch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/scripts/postprocess/qwen2_audio_jsonl_standardizer_batch.py -------------------------------------------------------------------------------- /scripts/preprocess/dir2scp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/scripts/preprocess/dir2scp.py -------------------------------------------------------------------------------- /scripts/preprocess/dir2scp.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/scripts/preprocess/dir2scp.sh -------------------------------------------------------------------------------- /scripts/preprocess/jsonl2scp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/scripts/preprocess/jsonl2scp.py -------------------------------------------------------------------------------- /scripts/show_result.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/scripts/show_result.py -------------------------------------------------------------------------------- /scripts/survey/average_result.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/scripts/survey/average_result.py -------------------------------------------------------------------------------- /scripts/survey/get_wer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/scripts/survey/get_wer.py -------------------------------------------------------------------------------- /scripts/survey/prepare_audioset-test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/scripts/survey/prepare_audioset-test.py -------------------------------------------------------------------------------- /scripts/survey/prepare_librispeech-test-clean.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/scripts/survey/prepare_librispeech-test-clean.py -------------------------------------------------------------------------------- /scripts/survey/prepare_musdb.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/scripts/survey/prepare_musdb.py -------------------------------------------------------------------------------- /scripts/visualization/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/scripts/visualization/README.md -------------------------------------------------------------------------------- /scripts/visualization/build_metricsTree.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/scripts/visualization/build_metricsTree.py -------------------------------------------------------------------------------- /scripts/visualization/radar_chart.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/scripts/visualization/radar_chart.png -------------------------------------------------------------------------------- /scripts/visualization/radar_chart.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/scripts/visualization/radar_chart.py -------------------------------------------------------------------------------- /scripts/visualization/requirements.txt: -------------------------------------------------------------------------------- 1 | plotly 2 | -------------------------------------------------------------------------------- /scripts/visualization/sample_sunburstchart.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/scripts/visualization/sample_sunburstchart.png -------------------------------------------------------------------------------- /scripts/visualization/sunburst_chart.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/scripts/visualization/sunburst_chart.py -------------------------------------------------------------------------------- /setup.cfg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/setup.cfg -------------------------------------------------------------------------------- /setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/setup.py -------------------------------------------------------------------------------- /test/test_general.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/test/test_general.py -------------------------------------------------------------------------------- /test/test_metrics/test_asr_matching.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/test/test_metrics/test_asr_matching.py -------------------------------------------------------------------------------- /test/test_metrics/test_cdpam.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/test/test_metrics/test_cdpam.py -------------------------------------------------------------------------------- /test/test_metrics/test_discrete_speech.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/test/test_metrics/test_discrete_speech.py -------------------------------------------------------------------------------- /test/test_metrics/test_dnsmos_pro.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/test/test_metrics/test_dnsmos_pro.py -------------------------------------------------------------------------------- /test/test_metrics/test_dpam.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/test/test_metrics/test_dpam.py -------------------------------------------------------------------------------- /test/test_metrics/test_emo_vad.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/test/test_metrics/test_emo_vad.py -------------------------------------------------------------------------------- /test/test_metrics/test_stoi.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/test/test_metrics/test_stoi.py -------------------------------------------------------------------------------- /test/test_pipeline/test_asr_match.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/test/test_pipeline/test_asr_match.py -------------------------------------------------------------------------------- /test/test_pipeline/test_asvspoof.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/test/test_pipeline/test_asvspoof.py -------------------------------------------------------------------------------- /test/test_pipeline/test_audiobox_aesthetics.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/test/test_pipeline/test_audiobox_aesthetics.py -------------------------------------------------------------------------------- /test/test_pipeline/test_emo_similarity.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/test/test_pipeline/test_emo_similarity.py -------------------------------------------------------------------------------- /test/test_pipeline/test_fad.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/test/test_pipeline/test_fad.py -------------------------------------------------------------------------------- /test/test_pipeline/test_general.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/test/test_pipeline/test_general.py -------------------------------------------------------------------------------- /test/test_pipeline/test_lid.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/test/test_pipeline/test_lid.py -------------------------------------------------------------------------------- /test/test_pipeline/test_nisqa.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/test/test_pipeline/test_nisqa.py -------------------------------------------------------------------------------- /test/test_pipeline/test_nomad.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/test/test_pipeline/test_nomad.py -------------------------------------------------------------------------------- /test/test_pipeline/test_noresqa.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/test/test_pipeline/test_noresqa.py -------------------------------------------------------------------------------- /test/test_pipeline/test_pam.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/test/test_pipeline/test_pam.py -------------------------------------------------------------------------------- /test/test_pipeline/test_pysepm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/test/test_pipeline/test_pysepm.py -------------------------------------------------------------------------------- /test/test_pipeline/test_qwen2_audio.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/test/test_pipeline/test_qwen2_audio.py -------------------------------------------------------------------------------- /test/test_pipeline/test_scoreq.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/test/test_pipeline/test_scoreq.py -------------------------------------------------------------------------------- /test/test_pipeline/test_sigmos.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/test/test_pipeline/test_sigmos.py -------------------------------------------------------------------------------- /test/test_pipeline/test_speaking_rate.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/test/test_pipeline/test_speaking_rate.py -------------------------------------------------------------------------------- /test/test_pipeline/test_srmr.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/test/test_pipeline/test_srmr.py -------------------------------------------------------------------------------- /test/test_pipeline/test_utmosv2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/test/test_pipeline/test_utmosv2.py -------------------------------------------------------------------------------- /test/test_pipeline/test_vad.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/test/test_pipeline/test_vad.py -------------------------------------------------------------------------------- /test/test_pipeline/test_vqscore.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/test/test_pipeline/test_vqscore.py -------------------------------------------------------------------------------- /test/test_pipeline/test_warpq.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/test/test_pipeline/test_warpq.py -------------------------------------------------------------------------------- /test/test_pipeline/test_wer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/test/test_pipeline/test_wer.py -------------------------------------------------------------------------------- /test/test_pipeline/test_wvmos.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/test/test_pipeline/test_wvmos.py -------------------------------------------------------------------------------- /test/test_samples/test1.scp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/test/test_samples/test1.scp -------------------------------------------------------------------------------- /test/test_samples/test1/test.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/test/test_samples/test1/test.wav -------------------------------------------------------------------------------- /test/test_samples/test2.scp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/test/test_samples/test2.scp -------------------------------------------------------------------------------- /test/test_samples/test2/test.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/test/test_samples/test2/test.wav -------------------------------------------------------------------------------- /test/test_samples/test_result.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/test/test_samples/test_result.txt -------------------------------------------------------------------------------- /test/test_samples/text: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/test/test_samples/text -------------------------------------------------------------------------------- /todo.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/todo.txt -------------------------------------------------------------------------------- /tools/activate_utmosv2.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/tools/activate_utmosv2.sh -------------------------------------------------------------------------------- /tools/easy_install.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/tools/easy_install.sh -------------------------------------------------------------------------------- /tools/install_asvspoof.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/tools/install_asvspoof.sh -------------------------------------------------------------------------------- /tools/install_audiobox-aesthetics.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/tools/install_audiobox-aesthetics.sh -------------------------------------------------------------------------------- /tools/install_emo2vec.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/tools/install_emo2vec.sh -------------------------------------------------------------------------------- /tools/install_fadtk.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/tools/install_fadtk.sh -------------------------------------------------------------------------------- /tools/install_fairseq.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/tools/install_fairseq.sh -------------------------------------------------------------------------------- /tools/install_gitlfs.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/tools/install_gitlfs.md -------------------------------------------------------------------------------- /tools/install_nomad.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/tools/install_nomad.sh -------------------------------------------------------------------------------- /tools/install_noresqa.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/tools/install_noresqa.sh -------------------------------------------------------------------------------- /tools/install_pyannote.sh: -------------------------------------------------------------------------------- 1 | #/bin/bash 2 | 3 | pip install pyannote 4 | -------------------------------------------------------------------------------- /tools/install_pysepm.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/tools/install_pysepm.sh -------------------------------------------------------------------------------- /tools/install_scoreq.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/tools/install_scoreq.sh -------------------------------------------------------------------------------- /tools/install_srmr.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/tools/install_srmr.sh -------------------------------------------------------------------------------- /tools/install_ssl-singer-identity.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/tools/install_ssl-singer-identity.sh -------------------------------------------------------------------------------- /tools/install_utmosv2.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/tools/install_utmosv2.sh -------------------------------------------------------------------------------- /tools/install_visqol.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/tools/install_visqol.md -------------------------------------------------------------------------------- /tools/install_warpq.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/tools/install_warpq.sh -------------------------------------------------------------------------------- /tools/install_wvmos.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/tools/install_wvmos.sh -------------------------------------------------------------------------------- /tools/pysepm/pysepm/intelligibilityMeasures.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/tools/pysepm/pysepm/intelligibilityMeasures.py -------------------------------------------------------------------------------- /tools/setup_nisqa.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/tools/setup_nisqa.sh -------------------------------------------------------------------------------- /versa/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/versa/__init__.py -------------------------------------------------------------------------------- /versa/bin/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /versa/bin/aggregate_results.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/versa/bin/aggregate_results.py -------------------------------------------------------------------------------- /versa/bin/scorer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/versa/bin/scorer.py -------------------------------------------------------------------------------- /versa/bin/scorer_chunk.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/versa/bin/scorer_chunk.py -------------------------------------------------------------------------------- /versa/corpus_metrics/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /versa/corpus_metrics/clap_score.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /versa/corpus_metrics/espnet_wer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/versa/corpus_metrics/espnet_wer.py -------------------------------------------------------------------------------- /versa/corpus_metrics/fad.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/versa/corpus_metrics/fad.py -------------------------------------------------------------------------------- /versa/corpus_metrics/individual_fad.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /versa/corpus_metrics/kid.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/versa/corpus_metrics/kid.py -------------------------------------------------------------------------------- /versa/corpus_metrics/owsm_wer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/versa/corpus_metrics/owsm_wer.py -------------------------------------------------------------------------------- /versa/corpus_metrics/test: -------------------------------------------------------------------------------- 1 | ../../test -------------------------------------------------------------------------------- /versa/corpus_metrics/whisper_wer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/versa/corpus_metrics/whisper_wer.py -------------------------------------------------------------------------------- /versa/metrics.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/versa/metrics.py -------------------------------------------------------------------------------- /versa/scorer_shared.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/versa/scorer_shared.py -------------------------------------------------------------------------------- /versa/sequence_metrics/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /versa/sequence_metrics/mcd_f0.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/versa/sequence_metrics/mcd_f0.py -------------------------------------------------------------------------------- /versa/sequence_metrics/signal_metric.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/versa/sequence_metrics/signal_metric.py -------------------------------------------------------------------------------- /versa/sequence_metrics/warpq.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/versa/sequence_metrics/warpq.py -------------------------------------------------------------------------------- /versa/utils_shared.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/versa/utils_shared.py -------------------------------------------------------------------------------- /versa/utterance_metrics/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /versa/utterance_metrics/arecho.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/versa/utterance_metrics/arecho.py -------------------------------------------------------------------------------- /versa/utterance_metrics/asr_matching.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/versa/utterance_metrics/asr_matching.py -------------------------------------------------------------------------------- /versa/utterance_metrics/asvspoof_score.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/versa/utterance_metrics/asvspoof_score.py -------------------------------------------------------------------------------- /versa/utterance_metrics/audiobox_aesthetics_score.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/versa/utterance_metrics/audiobox_aesthetics_score.py -------------------------------------------------------------------------------- /versa/utterance_metrics/cdpam_distance.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/versa/utterance_metrics/cdpam_distance.py -------------------------------------------------------------------------------- /versa/utterance_metrics/chroma_alignment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/versa/utterance_metrics/chroma_alignment.py -------------------------------------------------------------------------------- /versa/utterance_metrics/discrete_speech.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/versa/utterance_metrics/discrete_speech.py -------------------------------------------------------------------------------- /versa/utterance_metrics/dpam_distance.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/versa/utterance_metrics/dpam_distance.py -------------------------------------------------------------------------------- /versa/utterance_metrics/emo_vad.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/versa/utterance_metrics/emo_vad.py -------------------------------------------------------------------------------- /versa/utterance_metrics/emotion.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/versa/utterance_metrics/emotion.py -------------------------------------------------------------------------------- /versa/utterance_metrics/log_wmse.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/versa/utterance_metrics/log_wmse.py -------------------------------------------------------------------------------- /versa/utterance_metrics/nisqa.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/versa/utterance_metrics/nisqa.py -------------------------------------------------------------------------------- /versa/utterance_metrics/nisqa_utils/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /versa/utterance_metrics/nisqa_utils/nisqa_lib.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/versa/utterance_metrics/nisqa_utils/nisqa_lib.py -------------------------------------------------------------------------------- /versa/utterance_metrics/nomad.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/versa/utterance_metrics/nomad.py -------------------------------------------------------------------------------- /versa/utterance_metrics/noresqa.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/versa/utterance_metrics/noresqa.py -------------------------------------------------------------------------------- /versa/utterance_metrics/owsm_lid.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/versa/utterance_metrics/owsm_lid.py -------------------------------------------------------------------------------- /versa/utterance_metrics/pam.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/versa/utterance_metrics/pam.py -------------------------------------------------------------------------------- /versa/utterance_metrics/pam_utils/clap.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/versa/utterance_metrics/pam_utils/clap.py -------------------------------------------------------------------------------- /versa/utterance_metrics/pesq_score.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/versa/utterance_metrics/pesq_score.py -------------------------------------------------------------------------------- /versa/utterance_metrics/pseudo_mos.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/versa/utterance_metrics/pseudo_mos.py -------------------------------------------------------------------------------- /versa/utterance_metrics/pysepm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/versa/utterance_metrics/pysepm.py -------------------------------------------------------------------------------- /versa/utterance_metrics/qwen2_audio.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/versa/utterance_metrics/qwen2_audio.py -------------------------------------------------------------------------------- /versa/utterance_metrics/qwen_omni.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/versa/utterance_metrics/qwen_omni.py -------------------------------------------------------------------------------- /versa/utterance_metrics/scoreq.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/versa/utterance_metrics/scoreq.py -------------------------------------------------------------------------------- /versa/utterance_metrics/se_snr.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/versa/utterance_metrics/se_snr.py -------------------------------------------------------------------------------- /versa/utterance_metrics/sheet_ssqa.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/versa/utterance_metrics/sheet_ssqa.py -------------------------------------------------------------------------------- /versa/utterance_metrics/sigmos.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/versa/utterance_metrics/sigmos.py -------------------------------------------------------------------------------- /versa/utterance_metrics/singer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/versa/utterance_metrics/singer.py -------------------------------------------------------------------------------- /versa/utterance_metrics/speaker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/versa/utterance_metrics/speaker.py -------------------------------------------------------------------------------- /versa/utterance_metrics/speaking_rate.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/versa/utterance_metrics/speaking_rate.py -------------------------------------------------------------------------------- /versa/utterance_metrics/squim.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/versa/utterance_metrics/squim.py -------------------------------------------------------------------------------- /versa/utterance_metrics/srmr.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/versa/utterance_metrics/srmr.py -------------------------------------------------------------------------------- /versa/utterance_metrics/stoi.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/versa/utterance_metrics/stoi.py -------------------------------------------------------------------------------- /versa/utterance_metrics/universa.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/versa/utterance_metrics/universa.py -------------------------------------------------------------------------------- /versa/utterance_metrics/vad.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/versa/utterance_metrics/vad.py -------------------------------------------------------------------------------- /versa/utterance_metrics/visqol_score.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/versa/utterance_metrics/visqol_score.py -------------------------------------------------------------------------------- /versa/utterance_metrics/vqscore.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/versa/utterance_metrics/vqscore.py -------------------------------------------------------------------------------- /versa/utterance_metrics/wvmos.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wavlab-speech/versa/HEAD/versa/utterance_metrics/wvmos.py --------------------------------------------------------------------------------