├── .gitattributes ├── .github └── workflows │ ├── github-release.yml │ └── pypi-release.yml ├── .gitignore ├── Dockerfile ├── LICENSE ├── README.md ├── dualcodec.png ├── dualcodec ├── __init__.py ├── app.py ├── conf │ ├── data │ │ └── emilia_hf_raw_audio_static_batch.yaml │ ├── dualcodec_ft_12hzv1.yaml │ ├── dualcodec_ft_25hzv1.yaml │ ├── dualcodec_train.yaml │ ├── machine │ │ └── devbox.yaml │ ├── model │ │ ├── dualcodec_12hz_16384_4096_8vq.yaml │ │ └── dualcodec_25hz_16384_1024_12vq.yaml │ └── trainer │ │ └── codec_model_trainer.yaml ├── conf_tts │ └── model │ │ ├── flattened_ar │ │ └── llama_1x32768.yaml │ │ ├── valle_ar │ │ └── llama_250M.yaml │ │ └── valle_nar │ │ └── valle_nar.yaml ├── dataset │ ├── dataset.py │ ├── emilia_hf.py │ ├── file_utils.py │ └── processor.py ├── infer │ ├── dualcodec │ │ ├── get_model.py │ │ └── inference_with_semantic.py │ ├── examples │ │ └── basic │ │ │ ├── example_wav_en.wav │ │ │ └── example_wav_zh.wav │ ├── flattened_ar │ │ ├── flatten_patterns.py │ │ ├── inference_flattened.py │ │ ├── llama_wrapper.py │ │ ├── trainer.py │ │ └── utils_flattened_ar_infer.py │ ├── valle │ │ ├── api.py │ │ ├── cli_valle_infer.py │ │ ├── f5tts_gradio.py │ │ ├── gradio_valle_demo.py │ │ └── utils_valle_infer.py │ └── voicebox │ │ ├── cli_voicebox_infer.py │ │ └── utils_voicebox_infer.py ├── model_codec │ ├── __init__.py │ ├── cnn.py │ ├── dac_layers.py │ ├── dac_model.py │ ├── dac_quantize.py │ ├── discriminator.py │ ├── dualcodec_model.py │ ├── loss.py │ └── trainer.py ├── model_tts │ ├── valle_ar │ │ └── llama_wrapper.py │ ├── valle_nar │ │ ├── modeling_llama.py │ │ └── valle_nar_model.py │ └── voicebox │ │ ├── llama_nar.py │ │ ├── modeling_llama.py │ │ ├── vocoder_model.py │ │ └── voicebox_models.py └── utils │ ├── __init__.py │ ├── base_trainer.py │ ├── frontend_utils.py │ ├── melspec.py │ ├── normalization │ ├── en.py │ ├── global_punct.py │ └── zh.py │ ├── utils.py │ └── utils_infer.py ├── example.ipynb ├── losscurve1.png ├── losscurve2.png ├── pyproject.toml ├── setup.py └── train.py /.gitattributes: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jiaqili3/DualCodec/HEAD/.gitattributes -------------------------------------------------------------------------------- /.github/workflows/github-release.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jiaqili3/DualCodec/HEAD/.github/workflows/github-release.yml -------------------------------------------------------------------------------- /.github/workflows/pypi-release.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jiaqili3/DualCodec/HEAD/.github/workflows/pypi-release.yml -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jiaqili3/DualCodec/HEAD/.gitignore -------------------------------------------------------------------------------- /Dockerfile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jiaqili3/DualCodec/HEAD/Dockerfile -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jiaqili3/DualCodec/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jiaqili3/DualCodec/HEAD/README.md -------------------------------------------------------------------------------- /dualcodec.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jiaqili3/DualCodec/HEAD/dualcodec.png -------------------------------------------------------------------------------- /dualcodec/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jiaqili3/DualCodec/HEAD/dualcodec/__init__.py -------------------------------------------------------------------------------- /dualcodec/app.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jiaqili3/DualCodec/HEAD/dualcodec/app.py -------------------------------------------------------------------------------- /dualcodec/conf/data/emilia_hf_raw_audio_static_batch.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jiaqili3/DualCodec/HEAD/dualcodec/conf/data/emilia_hf_raw_audio_static_batch.yaml -------------------------------------------------------------------------------- /dualcodec/conf/dualcodec_ft_12hzv1.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jiaqili3/DualCodec/HEAD/dualcodec/conf/dualcodec_ft_12hzv1.yaml -------------------------------------------------------------------------------- /dualcodec/conf/dualcodec_ft_25hzv1.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jiaqili3/DualCodec/HEAD/dualcodec/conf/dualcodec_ft_25hzv1.yaml -------------------------------------------------------------------------------- /dualcodec/conf/dualcodec_train.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jiaqili3/DualCodec/HEAD/dualcodec/conf/dualcodec_train.yaml -------------------------------------------------------------------------------- /dualcodec/conf/machine/devbox.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jiaqili3/DualCodec/HEAD/dualcodec/conf/machine/devbox.yaml -------------------------------------------------------------------------------- /dualcodec/conf/model/dualcodec_12hz_16384_4096_8vq.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jiaqili3/DualCodec/HEAD/dualcodec/conf/model/dualcodec_12hz_16384_4096_8vq.yaml -------------------------------------------------------------------------------- /dualcodec/conf/model/dualcodec_25hz_16384_1024_12vq.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jiaqili3/DualCodec/HEAD/dualcodec/conf/model/dualcodec_25hz_16384_1024_12vq.yaml -------------------------------------------------------------------------------- /dualcodec/conf/trainer/codec_model_trainer.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jiaqili3/DualCodec/HEAD/dualcodec/conf/trainer/codec_model_trainer.yaml -------------------------------------------------------------------------------- /dualcodec/conf_tts/model/flattened_ar/llama_1x32768.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jiaqili3/DualCodec/HEAD/dualcodec/conf_tts/model/flattened_ar/llama_1x32768.yaml -------------------------------------------------------------------------------- /dualcodec/conf_tts/model/valle_ar/llama_250M.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jiaqili3/DualCodec/HEAD/dualcodec/conf_tts/model/valle_ar/llama_250M.yaml -------------------------------------------------------------------------------- /dualcodec/conf_tts/model/valle_nar/valle_nar.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jiaqili3/DualCodec/HEAD/dualcodec/conf_tts/model/valle_nar/valle_nar.yaml -------------------------------------------------------------------------------- /dualcodec/dataset/dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jiaqili3/DualCodec/HEAD/dualcodec/dataset/dataset.py -------------------------------------------------------------------------------- /dualcodec/dataset/emilia_hf.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jiaqili3/DualCodec/HEAD/dualcodec/dataset/emilia_hf.py -------------------------------------------------------------------------------- /dualcodec/dataset/file_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jiaqili3/DualCodec/HEAD/dualcodec/dataset/file_utils.py -------------------------------------------------------------------------------- /dualcodec/dataset/processor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jiaqili3/DualCodec/HEAD/dualcodec/dataset/processor.py -------------------------------------------------------------------------------- /dualcodec/infer/dualcodec/get_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jiaqili3/DualCodec/HEAD/dualcodec/infer/dualcodec/get_model.py -------------------------------------------------------------------------------- /dualcodec/infer/dualcodec/inference_with_semantic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jiaqili3/DualCodec/HEAD/dualcodec/infer/dualcodec/inference_with_semantic.py -------------------------------------------------------------------------------- /dualcodec/infer/examples/basic/example_wav_en.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jiaqili3/DualCodec/HEAD/dualcodec/infer/examples/basic/example_wav_en.wav -------------------------------------------------------------------------------- /dualcodec/infer/examples/basic/example_wav_zh.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jiaqili3/DualCodec/HEAD/dualcodec/infer/examples/basic/example_wav_zh.wav -------------------------------------------------------------------------------- /dualcodec/infer/flattened_ar/flatten_patterns.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jiaqili3/DualCodec/HEAD/dualcodec/infer/flattened_ar/flatten_patterns.py -------------------------------------------------------------------------------- /dualcodec/infer/flattened_ar/inference_flattened.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jiaqili3/DualCodec/HEAD/dualcodec/infer/flattened_ar/inference_flattened.py -------------------------------------------------------------------------------- /dualcodec/infer/flattened_ar/llama_wrapper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jiaqili3/DualCodec/HEAD/dualcodec/infer/flattened_ar/llama_wrapper.py -------------------------------------------------------------------------------- /dualcodec/infer/flattened_ar/trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jiaqili3/DualCodec/HEAD/dualcodec/infer/flattened_ar/trainer.py -------------------------------------------------------------------------------- /dualcodec/infer/flattened_ar/utils_flattened_ar_infer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jiaqili3/DualCodec/HEAD/dualcodec/infer/flattened_ar/utils_flattened_ar_infer.py -------------------------------------------------------------------------------- /dualcodec/infer/valle/api.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jiaqili3/DualCodec/HEAD/dualcodec/infer/valle/api.py -------------------------------------------------------------------------------- /dualcodec/infer/valle/cli_valle_infer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jiaqili3/DualCodec/HEAD/dualcodec/infer/valle/cli_valle_infer.py -------------------------------------------------------------------------------- /dualcodec/infer/valle/f5tts_gradio.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jiaqili3/DualCodec/HEAD/dualcodec/infer/valle/f5tts_gradio.py -------------------------------------------------------------------------------- /dualcodec/infer/valle/gradio_valle_demo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jiaqili3/DualCodec/HEAD/dualcodec/infer/valle/gradio_valle_demo.py -------------------------------------------------------------------------------- /dualcodec/infer/valle/utils_valle_infer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jiaqili3/DualCodec/HEAD/dualcodec/infer/valle/utils_valle_infer.py -------------------------------------------------------------------------------- /dualcodec/infer/voicebox/cli_voicebox_infer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jiaqili3/DualCodec/HEAD/dualcodec/infer/voicebox/cli_voicebox_infer.py -------------------------------------------------------------------------------- /dualcodec/infer/voicebox/utils_voicebox_infer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jiaqili3/DualCodec/HEAD/dualcodec/infer/voicebox/utils_voicebox_infer.py -------------------------------------------------------------------------------- /dualcodec/model_codec/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jiaqili3/DualCodec/HEAD/dualcodec/model_codec/__init__.py -------------------------------------------------------------------------------- /dualcodec/model_codec/cnn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jiaqili3/DualCodec/HEAD/dualcodec/model_codec/cnn.py -------------------------------------------------------------------------------- /dualcodec/model_codec/dac_layers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jiaqili3/DualCodec/HEAD/dualcodec/model_codec/dac_layers.py -------------------------------------------------------------------------------- /dualcodec/model_codec/dac_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jiaqili3/DualCodec/HEAD/dualcodec/model_codec/dac_model.py -------------------------------------------------------------------------------- /dualcodec/model_codec/dac_quantize.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jiaqili3/DualCodec/HEAD/dualcodec/model_codec/dac_quantize.py -------------------------------------------------------------------------------- /dualcodec/model_codec/discriminator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jiaqili3/DualCodec/HEAD/dualcodec/model_codec/discriminator.py -------------------------------------------------------------------------------- /dualcodec/model_codec/dualcodec_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jiaqili3/DualCodec/HEAD/dualcodec/model_codec/dualcodec_model.py -------------------------------------------------------------------------------- /dualcodec/model_codec/loss.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jiaqili3/DualCodec/HEAD/dualcodec/model_codec/loss.py -------------------------------------------------------------------------------- /dualcodec/model_codec/trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jiaqili3/DualCodec/HEAD/dualcodec/model_codec/trainer.py -------------------------------------------------------------------------------- /dualcodec/model_tts/valle_ar/llama_wrapper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jiaqili3/DualCodec/HEAD/dualcodec/model_tts/valle_ar/llama_wrapper.py -------------------------------------------------------------------------------- /dualcodec/model_tts/valle_nar/modeling_llama.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jiaqili3/DualCodec/HEAD/dualcodec/model_tts/valle_nar/modeling_llama.py -------------------------------------------------------------------------------- /dualcodec/model_tts/valle_nar/valle_nar_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jiaqili3/DualCodec/HEAD/dualcodec/model_tts/valle_nar/valle_nar_model.py -------------------------------------------------------------------------------- /dualcodec/model_tts/voicebox/llama_nar.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jiaqili3/DualCodec/HEAD/dualcodec/model_tts/voicebox/llama_nar.py -------------------------------------------------------------------------------- /dualcodec/model_tts/voicebox/modeling_llama.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jiaqili3/DualCodec/HEAD/dualcodec/model_tts/voicebox/modeling_llama.py -------------------------------------------------------------------------------- /dualcodec/model_tts/voicebox/vocoder_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jiaqili3/DualCodec/HEAD/dualcodec/model_tts/voicebox/vocoder_model.py -------------------------------------------------------------------------------- /dualcodec/model_tts/voicebox/voicebox_models.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jiaqili3/DualCodec/HEAD/dualcodec/model_tts/voicebox/voicebox_models.py -------------------------------------------------------------------------------- /dualcodec/utils/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jiaqili3/DualCodec/HEAD/dualcodec/utils/__init__.py -------------------------------------------------------------------------------- /dualcodec/utils/base_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jiaqili3/DualCodec/HEAD/dualcodec/utils/base_trainer.py -------------------------------------------------------------------------------- /dualcodec/utils/frontend_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jiaqili3/DualCodec/HEAD/dualcodec/utils/frontend_utils.py -------------------------------------------------------------------------------- /dualcodec/utils/melspec.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jiaqili3/DualCodec/HEAD/dualcodec/utils/melspec.py -------------------------------------------------------------------------------- /dualcodec/utils/normalization/en.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jiaqili3/DualCodec/HEAD/dualcodec/utils/normalization/en.py -------------------------------------------------------------------------------- /dualcodec/utils/normalization/global_punct.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jiaqili3/DualCodec/HEAD/dualcodec/utils/normalization/global_punct.py -------------------------------------------------------------------------------- /dualcodec/utils/normalization/zh.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jiaqili3/DualCodec/HEAD/dualcodec/utils/normalization/zh.py -------------------------------------------------------------------------------- /dualcodec/utils/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jiaqili3/DualCodec/HEAD/dualcodec/utils/utils.py -------------------------------------------------------------------------------- /dualcodec/utils/utils_infer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jiaqili3/DualCodec/HEAD/dualcodec/utils/utils_infer.py -------------------------------------------------------------------------------- /example.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jiaqili3/DualCodec/HEAD/example.ipynb -------------------------------------------------------------------------------- /losscurve1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jiaqili3/DualCodec/HEAD/losscurve1.png -------------------------------------------------------------------------------- /losscurve2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jiaqili3/DualCodec/HEAD/losscurve2.png -------------------------------------------------------------------------------- /pyproject.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jiaqili3/DualCodec/HEAD/pyproject.toml -------------------------------------------------------------------------------- /setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jiaqili3/DualCodec/HEAD/setup.py -------------------------------------------------------------------------------- /train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jiaqili3/DualCodec/HEAD/train.py --------------------------------------------------------------------------------