├── .github └── workflows │ └── test.yml ├── .gitignore ├── .gitmodules ├── LICENSE ├── README.md ├── boson_multimodal ├── __init__.py ├── audio_processing │ ├── LICENSE │ ├── descriptaudiocodec │ │ ├── __init__.py │ │ └── dac │ │ │ ├── model │ │ │ ├── base.py │ │ │ └── dac.py │ │ │ └── nn │ │ │ ├── layers.py │ │ │ └── quantize.py │ ├── higgs_audio_tokenizer.py │ ├── quantization │ │ ├── __init__.py │ │ ├── ac.py │ │ ├── core_vq.py │ │ ├── core_vq_lsx_version.py │ │ ├── ddp_utils.py │ │ ├── distrib.py │ │ └── vq.py │ └── semantic_module.py ├── constants.py ├── data_collator │ ├── __init__.py │ └── higgs_audio_collator.py ├── data_types.py ├── dataset │ ├── __init__.py │ └── chatml_dataset.py ├── generation.py ├── model │ ├── __init__.py │ └── higgs_audio │ │ ├── __init__.py │ │ ├── audio_head.py │ │ ├── common.py │ │ ├── configuration_higgs_audio.py │ │ ├── cuda_graph_runner.py │ │ ├── custom_modules.py │ │ ├── modeling_higgs_audio.py │ │ └── utils.py └── serve │ ├── serve_engine.py │ └── utils.py ├── examples ├── README.md ├── generation.py ├── scene_prompts │ ├── quiet_indoor.txt │ └── reading_blog.txt ├── serve_engine │ ├── README.md │ ├── input_samples.py │ ├── run_hf_example.py │ └── voice_examples │ │ └── old_man.wav ├── server.py ├── test.html ├── transcript │ ├── multi_speaker │ │ ├── en_argument.txt │ │ └── en_higgs.txt │ └── single_speaker │ │ ├── en_basic.txt │ │ ├── en_dl.txt │ │ ├── en_higgs_audio_blog.md │ │ ├── experimental │ │ ├── en_bgm.txt │ │ └── en_humming.txt │ │ └── zh_ai.txt ├── vllm │ ├── README.md │ └── run_chat_completion.py └── voice_prompts │ ├── belinda.txt │ ├── belinda.wav │ ├── bigbang_amy.txt │ ├── bigbang_amy.wav │ ├── bigbang_sheldon.txt │ ├── bigbang_sheldon.wav │ ├── broom_salesman.txt │ ├── broom_salesman.wav │ ├── chadwick.txt │ ├── chadwick.wav │ ├── en_man.txt │ ├── en_man.wav │ ├── en_woman.txt │ ├── en_woman.wav │ ├── fiftyshades_anna.txt │ ├── fiftyshades_anna.wav │ ├── mabaoguo.txt │ ├── mabaoguo.wav │ ├── mabel.txt │ ├── mabel.wav │ ├── profile.yaml │ ├── shrek_donkey.txt │ ├── shrek_donkey.wav │ ├── shrek_donkey_es.txt │ ├── shrek_donkey_es.wav │ ├── shrek_fiona.txt │ ├── shrek_fiona.wav │ ├── shrek_shrek.txt │ ├── shrek_shrek.wav │ ├── vex.txt │ ├── vex.wav │ ├── zh_man_sichuan.txt │ └── zh_man_sichuan.wav ├── figures ├── dual_ffn_comparison_seed_tts_en_sim.png ├── dual_ffn_comparison_seed_tts_en_wer.png ├── dual_ffn_comparison_seed_tts_zh_sim.png ├── dual_ffn_comparison_seed_tts_zh_wer.png ├── emergent-tts-emotions-win-rate.png ├── higgs_audio_tokenizer_architecture.png ├── higgs_audio_v2_architecture_combined.png └── higgs_audio_v2_open_source_delay_pattern.png ├── pyproject.toml ├── requirements.txt ├── setup.cfg ├── setup.py └── tech_blogs ├── ARCHITECTURE_BLOG.md └── TOKENIZER_BLOG.md /.github/workflows/test.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/.github/workflows/test.yml -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/.gitignore -------------------------------------------------------------------------------- /.gitmodules: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/README.md -------------------------------------------------------------------------------- /boson_multimodal/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /boson_multimodal/audio_processing/LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/boson_multimodal/audio_processing/LICENSE -------------------------------------------------------------------------------- /boson_multimodal/audio_processing/descriptaudiocodec/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /boson_multimodal/audio_processing/descriptaudiocodec/dac/model/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/boson_multimodal/audio_processing/descriptaudiocodec/dac/model/base.py -------------------------------------------------------------------------------- /boson_multimodal/audio_processing/descriptaudiocodec/dac/model/dac.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/boson_multimodal/audio_processing/descriptaudiocodec/dac/model/dac.py -------------------------------------------------------------------------------- /boson_multimodal/audio_processing/descriptaudiocodec/dac/nn/layers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/boson_multimodal/audio_processing/descriptaudiocodec/dac/nn/layers.py -------------------------------------------------------------------------------- /boson_multimodal/audio_processing/descriptaudiocodec/dac/nn/quantize.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/boson_multimodal/audio_processing/descriptaudiocodec/dac/nn/quantize.py -------------------------------------------------------------------------------- /boson_multimodal/audio_processing/higgs_audio_tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/boson_multimodal/audio_processing/higgs_audio_tokenizer.py -------------------------------------------------------------------------------- /boson_multimodal/audio_processing/quantization/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/boson_multimodal/audio_processing/quantization/__init__.py -------------------------------------------------------------------------------- /boson_multimodal/audio_processing/quantization/ac.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/boson_multimodal/audio_processing/quantization/ac.py -------------------------------------------------------------------------------- /boson_multimodal/audio_processing/quantization/core_vq.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/boson_multimodal/audio_processing/quantization/core_vq.py -------------------------------------------------------------------------------- /boson_multimodal/audio_processing/quantization/core_vq_lsx_version.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/boson_multimodal/audio_processing/quantization/core_vq_lsx_version.py -------------------------------------------------------------------------------- /boson_multimodal/audio_processing/quantization/ddp_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/boson_multimodal/audio_processing/quantization/ddp_utils.py -------------------------------------------------------------------------------- /boson_multimodal/audio_processing/quantization/distrib.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/boson_multimodal/audio_processing/quantization/distrib.py -------------------------------------------------------------------------------- /boson_multimodal/audio_processing/quantization/vq.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/boson_multimodal/audio_processing/quantization/vq.py -------------------------------------------------------------------------------- /boson_multimodal/audio_processing/semantic_module.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/boson_multimodal/audio_processing/semantic_module.py -------------------------------------------------------------------------------- /boson_multimodal/constants.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/boson_multimodal/constants.py -------------------------------------------------------------------------------- /boson_multimodal/data_collator/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /boson_multimodal/data_collator/higgs_audio_collator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/boson_multimodal/data_collator/higgs_audio_collator.py -------------------------------------------------------------------------------- /boson_multimodal/data_types.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/boson_multimodal/data_types.py -------------------------------------------------------------------------------- /boson_multimodal/dataset/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /boson_multimodal/dataset/chatml_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/boson_multimodal/dataset/chatml_dataset.py -------------------------------------------------------------------------------- /boson_multimodal/generation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/boson_multimodal/generation.py -------------------------------------------------------------------------------- /boson_multimodal/model/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /boson_multimodal/model/higgs_audio/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/boson_multimodal/model/higgs_audio/__init__.py -------------------------------------------------------------------------------- /boson_multimodal/model/higgs_audio/audio_head.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/boson_multimodal/model/higgs_audio/audio_head.py -------------------------------------------------------------------------------- /boson_multimodal/model/higgs_audio/common.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/boson_multimodal/model/higgs_audio/common.py -------------------------------------------------------------------------------- /boson_multimodal/model/higgs_audio/configuration_higgs_audio.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/boson_multimodal/model/higgs_audio/configuration_higgs_audio.py -------------------------------------------------------------------------------- /boson_multimodal/model/higgs_audio/cuda_graph_runner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/boson_multimodal/model/higgs_audio/cuda_graph_runner.py -------------------------------------------------------------------------------- /boson_multimodal/model/higgs_audio/custom_modules.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/boson_multimodal/model/higgs_audio/custom_modules.py -------------------------------------------------------------------------------- /boson_multimodal/model/higgs_audio/modeling_higgs_audio.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/boson_multimodal/model/higgs_audio/modeling_higgs_audio.py -------------------------------------------------------------------------------- /boson_multimodal/model/higgs_audio/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/boson_multimodal/model/higgs_audio/utils.py -------------------------------------------------------------------------------- /boson_multimodal/serve/serve_engine.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/boson_multimodal/serve/serve_engine.py -------------------------------------------------------------------------------- /boson_multimodal/serve/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/boson_multimodal/serve/utils.py -------------------------------------------------------------------------------- /examples/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/examples/README.md -------------------------------------------------------------------------------- /examples/generation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/examples/generation.py -------------------------------------------------------------------------------- /examples/scene_prompts/quiet_indoor.txt: -------------------------------------------------------------------------------- 1 | Audio is recorded from a quiet room. 2 | -------------------------------------------------------------------------------- /examples/scene_prompts/reading_blog.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/examples/scene_prompts/reading_blog.txt -------------------------------------------------------------------------------- /examples/serve_engine/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/examples/serve_engine/README.md -------------------------------------------------------------------------------- /examples/serve_engine/input_samples.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/examples/serve_engine/input_samples.py -------------------------------------------------------------------------------- /examples/serve_engine/run_hf_example.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/examples/serve_engine/run_hf_example.py -------------------------------------------------------------------------------- /examples/serve_engine/voice_examples/old_man.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/examples/serve_engine/voice_examples/old_man.wav -------------------------------------------------------------------------------- /examples/server.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/examples/server.py -------------------------------------------------------------------------------- /examples/test.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/examples/test.html -------------------------------------------------------------------------------- /examples/transcript/multi_speaker/en_argument.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/examples/transcript/multi_speaker/en_argument.txt -------------------------------------------------------------------------------- /examples/transcript/multi_speaker/en_higgs.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/examples/transcript/multi_speaker/en_higgs.txt -------------------------------------------------------------------------------- /examples/transcript/single_speaker/en_basic.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/examples/transcript/single_speaker/en_basic.txt -------------------------------------------------------------------------------- /examples/transcript/single_speaker/en_dl.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/examples/transcript/single_speaker/en_dl.txt -------------------------------------------------------------------------------- /examples/transcript/single_speaker/en_higgs_audio_blog.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/examples/transcript/single_speaker/en_higgs_audio_blog.md -------------------------------------------------------------------------------- /examples/transcript/single_speaker/experimental/en_bgm.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/examples/transcript/single_speaker/experimental/en_bgm.txt -------------------------------------------------------------------------------- /examples/transcript/single_speaker/experimental/en_humming.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/examples/transcript/single_speaker/experimental/en_humming.txt -------------------------------------------------------------------------------- /examples/transcript/single_speaker/zh_ai.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/examples/transcript/single_speaker/zh_ai.txt -------------------------------------------------------------------------------- /examples/vllm/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/examples/vllm/README.md -------------------------------------------------------------------------------- /examples/vllm/run_chat_completion.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/examples/vllm/run_chat_completion.py -------------------------------------------------------------------------------- /examples/voice_prompts/belinda.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/examples/voice_prompts/belinda.txt -------------------------------------------------------------------------------- /examples/voice_prompts/belinda.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/examples/voice_prompts/belinda.wav -------------------------------------------------------------------------------- /examples/voice_prompts/bigbang_amy.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/examples/voice_prompts/bigbang_amy.txt -------------------------------------------------------------------------------- /examples/voice_prompts/bigbang_amy.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/examples/voice_prompts/bigbang_amy.wav -------------------------------------------------------------------------------- /examples/voice_prompts/bigbang_sheldon.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/examples/voice_prompts/bigbang_sheldon.txt -------------------------------------------------------------------------------- /examples/voice_prompts/bigbang_sheldon.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/examples/voice_prompts/bigbang_sheldon.wav -------------------------------------------------------------------------------- /examples/voice_prompts/broom_salesman.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/examples/voice_prompts/broom_salesman.txt -------------------------------------------------------------------------------- /examples/voice_prompts/broom_salesman.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/examples/voice_prompts/broom_salesman.wav -------------------------------------------------------------------------------- /examples/voice_prompts/chadwick.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/examples/voice_prompts/chadwick.txt -------------------------------------------------------------------------------- /examples/voice_prompts/chadwick.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/examples/voice_prompts/chadwick.wav -------------------------------------------------------------------------------- /examples/voice_prompts/en_man.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/examples/voice_prompts/en_man.txt -------------------------------------------------------------------------------- /examples/voice_prompts/en_man.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/examples/voice_prompts/en_man.wav -------------------------------------------------------------------------------- /examples/voice_prompts/en_woman.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/examples/voice_prompts/en_woman.txt -------------------------------------------------------------------------------- /examples/voice_prompts/en_woman.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/examples/voice_prompts/en_woman.wav -------------------------------------------------------------------------------- /examples/voice_prompts/fiftyshades_anna.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/examples/voice_prompts/fiftyshades_anna.txt -------------------------------------------------------------------------------- /examples/voice_prompts/fiftyshades_anna.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/examples/voice_prompts/fiftyshades_anna.wav -------------------------------------------------------------------------------- /examples/voice_prompts/mabaoguo.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/examples/voice_prompts/mabaoguo.txt -------------------------------------------------------------------------------- /examples/voice_prompts/mabaoguo.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/examples/voice_prompts/mabaoguo.wav -------------------------------------------------------------------------------- /examples/voice_prompts/mabel.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/examples/voice_prompts/mabel.txt -------------------------------------------------------------------------------- /examples/voice_prompts/mabel.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/examples/voice_prompts/mabel.wav -------------------------------------------------------------------------------- /examples/voice_prompts/profile.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/examples/voice_prompts/profile.yaml -------------------------------------------------------------------------------- /examples/voice_prompts/shrek_donkey.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/examples/voice_prompts/shrek_donkey.txt -------------------------------------------------------------------------------- /examples/voice_prompts/shrek_donkey.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/examples/voice_prompts/shrek_donkey.wav -------------------------------------------------------------------------------- /examples/voice_prompts/shrek_donkey_es.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/examples/voice_prompts/shrek_donkey_es.txt -------------------------------------------------------------------------------- /examples/voice_prompts/shrek_donkey_es.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/examples/voice_prompts/shrek_donkey_es.wav -------------------------------------------------------------------------------- /examples/voice_prompts/shrek_fiona.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/examples/voice_prompts/shrek_fiona.txt -------------------------------------------------------------------------------- /examples/voice_prompts/shrek_fiona.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/examples/voice_prompts/shrek_fiona.wav -------------------------------------------------------------------------------- /examples/voice_prompts/shrek_shrek.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/examples/voice_prompts/shrek_shrek.txt -------------------------------------------------------------------------------- /examples/voice_prompts/shrek_shrek.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/examples/voice_prompts/shrek_shrek.wav -------------------------------------------------------------------------------- /examples/voice_prompts/vex.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/examples/voice_prompts/vex.txt -------------------------------------------------------------------------------- /examples/voice_prompts/vex.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/examples/voice_prompts/vex.wav -------------------------------------------------------------------------------- /examples/voice_prompts/zh_man_sichuan.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/examples/voice_prompts/zh_man_sichuan.txt -------------------------------------------------------------------------------- /examples/voice_prompts/zh_man_sichuan.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/examples/voice_prompts/zh_man_sichuan.wav -------------------------------------------------------------------------------- /figures/dual_ffn_comparison_seed_tts_en_sim.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/figures/dual_ffn_comparison_seed_tts_en_sim.png -------------------------------------------------------------------------------- /figures/dual_ffn_comparison_seed_tts_en_wer.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/figures/dual_ffn_comparison_seed_tts_en_wer.png -------------------------------------------------------------------------------- /figures/dual_ffn_comparison_seed_tts_zh_sim.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/figures/dual_ffn_comparison_seed_tts_zh_sim.png -------------------------------------------------------------------------------- /figures/dual_ffn_comparison_seed_tts_zh_wer.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/figures/dual_ffn_comparison_seed_tts_zh_wer.png -------------------------------------------------------------------------------- /figures/emergent-tts-emotions-win-rate.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/figures/emergent-tts-emotions-win-rate.png -------------------------------------------------------------------------------- /figures/higgs_audio_tokenizer_architecture.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/figures/higgs_audio_tokenizer_architecture.png -------------------------------------------------------------------------------- /figures/higgs_audio_v2_architecture_combined.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/figures/higgs_audio_v2_architecture_combined.png -------------------------------------------------------------------------------- /figures/higgs_audio_v2_open_source_delay_pattern.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/figures/higgs_audio_v2_open_source_delay_pattern.png -------------------------------------------------------------------------------- /pyproject.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/pyproject.toml -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/requirements.txt -------------------------------------------------------------------------------- /setup.cfg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/setup.cfg -------------------------------------------------------------------------------- /setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/setup.py -------------------------------------------------------------------------------- /tech_blogs/ARCHITECTURE_BLOG.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/tech_blogs/ARCHITECTURE_BLOG.md -------------------------------------------------------------------------------- /tech_blogs/TOKENIZER_BLOG.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Nyarlth/higgs-audio_quantized/HEAD/tech_blogs/TOKENIZER_BLOG.md --------------------------------------------------------------------------------