├── .gitignore ├── EXAMPLES.md ├── FINETUNING.md ├── Figures ├── MOS-preference.png ├── VibeVoice.jpg ├── VibeVoice_logo.png └── VibeVoice_logo_white.png ├── LICENSE ├── README.md ├── demo ├── VibeVoice_colab.ipynb ├── example │ ├── 1p_EN2CH.mp4 │ ├── 2p_see_u_again.mp4 │ └── 4p_climate_45min.mp4 ├── gradio_demo.py ├── inference_from_file.py ├── text_examples │ ├── 1p_Ch2EN.txt │ ├── 1p_abs.txt │ ├── 2p_goat.txt │ ├── 2p_music.txt │ ├── 2p_short.txt │ ├── 2p_yayi.txt │ ├── 3p_gpt5.txt │ ├── 4p_climate_100min.txt │ └── 4p_climate_45min.txt └── voices │ ├── en-Alice_woman.wav │ ├── en-Carter_man.wav │ ├── en-Frank_man.wav │ ├── en-Mary_woman_bgm.wav │ ├── en-Maya_woman.wav │ ├── in-Samuel_man.wav │ ├── zh-Anchen_man_bgm.wav │ ├── zh-Bowen_man.wav │ └── zh-Xinran_woman.wav ├── pyproject.toml └── vibevoice ├── __init__.py ├── configs ├── qwen2.5_1.5b_64k.json └── qwen2.5_7b_32k.json ├── finetune ├── __init__.py ├── data_vibevoice.py └── train_vibevoice.py ├── modular ├── __init__.py ├── configuration_vibevoice.py ├── lora_loading.py ├── modeling_vibevoice.py ├── modeling_vibevoice_inference.py ├── modular_vibevoice_diffusion_head.py ├── modular_vibevoice_text_tokenizer.py ├── modular_vibevoice_tokenizer.py └── streamer.py ├── processor ├── __init__.py ├── vibevoice_processor.py └── vibevoice_tokenizer_processor.py ├── schedule ├── __init__.py ├── dpm_solver.py └── timestep_sampler.py └── scripts ├── __init__.py ├── convert_nnscaler_checkpoint_to_transformers.py └── merge_vibevoice_models.py /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vibevoice-community/VibeVoice/HEAD/.gitignore -------------------------------------------------------------------------------- /EXAMPLES.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vibevoice-community/VibeVoice/HEAD/EXAMPLES.md -------------------------------------------------------------------------------- /FINETUNING.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vibevoice-community/VibeVoice/HEAD/FINETUNING.md -------------------------------------------------------------------------------- /Figures/MOS-preference.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vibevoice-community/VibeVoice/HEAD/Figures/MOS-preference.png -------------------------------------------------------------------------------- /Figures/VibeVoice.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vibevoice-community/VibeVoice/HEAD/Figures/VibeVoice.jpg -------------------------------------------------------------------------------- /Figures/VibeVoice_logo.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vibevoice-community/VibeVoice/HEAD/Figures/VibeVoice_logo.png -------------------------------------------------------------------------------- /Figures/VibeVoice_logo_white.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vibevoice-community/VibeVoice/HEAD/Figures/VibeVoice_logo_white.png -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vibevoice-community/VibeVoice/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vibevoice-community/VibeVoice/HEAD/README.md -------------------------------------------------------------------------------- /demo/VibeVoice_colab.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vibevoice-community/VibeVoice/HEAD/demo/VibeVoice_colab.ipynb -------------------------------------------------------------------------------- /demo/example/1p_EN2CH.mp4: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vibevoice-community/VibeVoice/HEAD/demo/example/1p_EN2CH.mp4 -------------------------------------------------------------------------------- /demo/example/2p_see_u_again.mp4: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vibevoice-community/VibeVoice/HEAD/demo/example/2p_see_u_again.mp4 -------------------------------------------------------------------------------- /demo/example/4p_climate_45min.mp4: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vibevoice-community/VibeVoice/HEAD/demo/example/4p_climate_45min.mp4 -------------------------------------------------------------------------------- /demo/gradio_demo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vibevoice-community/VibeVoice/HEAD/demo/gradio_demo.py -------------------------------------------------------------------------------- /demo/inference_from_file.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vibevoice-community/VibeVoice/HEAD/demo/inference_from_file.py -------------------------------------------------------------------------------- /demo/text_examples/1p_Ch2EN.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vibevoice-community/VibeVoice/HEAD/demo/text_examples/1p_Ch2EN.txt -------------------------------------------------------------------------------- /demo/text_examples/1p_abs.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vibevoice-community/VibeVoice/HEAD/demo/text_examples/1p_abs.txt -------------------------------------------------------------------------------- /demo/text_examples/2p_goat.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vibevoice-community/VibeVoice/HEAD/demo/text_examples/2p_goat.txt -------------------------------------------------------------------------------- /demo/text_examples/2p_music.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vibevoice-community/VibeVoice/HEAD/demo/text_examples/2p_music.txt -------------------------------------------------------------------------------- /demo/text_examples/2p_short.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vibevoice-community/VibeVoice/HEAD/demo/text_examples/2p_short.txt -------------------------------------------------------------------------------- /demo/text_examples/2p_yayi.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vibevoice-community/VibeVoice/HEAD/demo/text_examples/2p_yayi.txt -------------------------------------------------------------------------------- /demo/text_examples/3p_gpt5.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vibevoice-community/VibeVoice/HEAD/demo/text_examples/3p_gpt5.txt -------------------------------------------------------------------------------- /demo/text_examples/4p_climate_100min.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vibevoice-community/VibeVoice/HEAD/demo/text_examples/4p_climate_100min.txt -------------------------------------------------------------------------------- /demo/text_examples/4p_climate_45min.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vibevoice-community/VibeVoice/HEAD/demo/text_examples/4p_climate_45min.txt -------------------------------------------------------------------------------- /demo/voices/en-Alice_woman.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vibevoice-community/VibeVoice/HEAD/demo/voices/en-Alice_woman.wav -------------------------------------------------------------------------------- /demo/voices/en-Carter_man.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vibevoice-community/VibeVoice/HEAD/demo/voices/en-Carter_man.wav -------------------------------------------------------------------------------- /demo/voices/en-Frank_man.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vibevoice-community/VibeVoice/HEAD/demo/voices/en-Frank_man.wav -------------------------------------------------------------------------------- /demo/voices/en-Mary_woman_bgm.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vibevoice-community/VibeVoice/HEAD/demo/voices/en-Mary_woman_bgm.wav -------------------------------------------------------------------------------- /demo/voices/en-Maya_woman.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vibevoice-community/VibeVoice/HEAD/demo/voices/en-Maya_woman.wav -------------------------------------------------------------------------------- /demo/voices/in-Samuel_man.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vibevoice-community/VibeVoice/HEAD/demo/voices/in-Samuel_man.wav -------------------------------------------------------------------------------- /demo/voices/zh-Anchen_man_bgm.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vibevoice-community/VibeVoice/HEAD/demo/voices/zh-Anchen_man_bgm.wav -------------------------------------------------------------------------------- /demo/voices/zh-Bowen_man.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vibevoice-community/VibeVoice/HEAD/demo/voices/zh-Bowen_man.wav -------------------------------------------------------------------------------- /demo/voices/zh-Xinran_woman.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vibevoice-community/VibeVoice/HEAD/demo/voices/zh-Xinran_woman.wav -------------------------------------------------------------------------------- /pyproject.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vibevoice-community/VibeVoice/HEAD/pyproject.toml -------------------------------------------------------------------------------- /vibevoice/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /vibevoice/configs/qwen2.5_1.5b_64k.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vibevoice-community/VibeVoice/HEAD/vibevoice/configs/qwen2.5_1.5b_64k.json -------------------------------------------------------------------------------- /vibevoice/configs/qwen2.5_7b_32k.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vibevoice-community/VibeVoice/HEAD/vibevoice/configs/qwen2.5_7b_32k.json -------------------------------------------------------------------------------- /vibevoice/finetune/__init__.py: -------------------------------------------------------------------------------- 1 | # VibeVoice finetuning module -------------------------------------------------------------------------------- /vibevoice/finetune/data_vibevoice.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vibevoice-community/VibeVoice/HEAD/vibevoice/finetune/data_vibevoice.py -------------------------------------------------------------------------------- /vibevoice/finetune/train_vibevoice.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vibevoice-community/VibeVoice/HEAD/vibevoice/finetune/train_vibevoice.py -------------------------------------------------------------------------------- /vibevoice/modular/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /vibevoice/modular/configuration_vibevoice.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vibevoice-community/VibeVoice/HEAD/vibevoice/modular/configuration_vibevoice.py -------------------------------------------------------------------------------- /vibevoice/modular/lora_loading.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vibevoice-community/VibeVoice/HEAD/vibevoice/modular/lora_loading.py -------------------------------------------------------------------------------- /vibevoice/modular/modeling_vibevoice.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vibevoice-community/VibeVoice/HEAD/vibevoice/modular/modeling_vibevoice.py -------------------------------------------------------------------------------- /vibevoice/modular/modeling_vibevoice_inference.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vibevoice-community/VibeVoice/HEAD/vibevoice/modular/modeling_vibevoice_inference.py -------------------------------------------------------------------------------- /vibevoice/modular/modular_vibevoice_diffusion_head.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vibevoice-community/VibeVoice/HEAD/vibevoice/modular/modular_vibevoice_diffusion_head.py -------------------------------------------------------------------------------- /vibevoice/modular/modular_vibevoice_text_tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vibevoice-community/VibeVoice/HEAD/vibevoice/modular/modular_vibevoice_text_tokenizer.py -------------------------------------------------------------------------------- /vibevoice/modular/modular_vibevoice_tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vibevoice-community/VibeVoice/HEAD/vibevoice/modular/modular_vibevoice_tokenizer.py -------------------------------------------------------------------------------- /vibevoice/modular/streamer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vibevoice-community/VibeVoice/HEAD/vibevoice/modular/streamer.py -------------------------------------------------------------------------------- /vibevoice/processor/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /vibevoice/processor/vibevoice_processor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vibevoice-community/VibeVoice/HEAD/vibevoice/processor/vibevoice_processor.py -------------------------------------------------------------------------------- /vibevoice/processor/vibevoice_tokenizer_processor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vibevoice-community/VibeVoice/HEAD/vibevoice/processor/vibevoice_tokenizer_processor.py -------------------------------------------------------------------------------- /vibevoice/schedule/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /vibevoice/schedule/dpm_solver.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vibevoice-community/VibeVoice/HEAD/vibevoice/schedule/dpm_solver.py -------------------------------------------------------------------------------- /vibevoice/schedule/timestep_sampler.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vibevoice-community/VibeVoice/HEAD/vibevoice/schedule/timestep_sampler.py -------------------------------------------------------------------------------- /vibevoice/scripts/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /vibevoice/scripts/convert_nnscaler_checkpoint_to_transformers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vibevoice-community/VibeVoice/HEAD/vibevoice/scripts/convert_nnscaler_checkpoint_to_transformers.py -------------------------------------------------------------------------------- /vibevoice/scripts/merge_vibevoice_models.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/vibevoice-community/VibeVoice/HEAD/vibevoice/scripts/merge_vibevoice_models.py --------------------------------------------------------------------------------