├── .gitignore ├── LICENSE ├── README.md ├── batch_eval.py ├── config ├── __init__.py ├── base_config.yaml ├── data │ └── base.yaml ├── eval_config.yaml ├── eval_data │ └── base.yaml ├── hydra │ └── job_logging │ │ ├── custom-eval.yaml │ │ ├── custom-no-rank.yaml │ │ ├── custom-simplest.yaml │ │ └── custom.yaml └── train_config.yaml ├── demo.py ├── docs ├── EVAL.md ├── MODELS.md ├── TRAINING.md ├── images │ └── icon.png ├── index.html ├── style.css ├── style_videos.css ├── video_demo.html ├── video_gen.html ├── video_main.html └── video_vgg.html ├── eval_onsets.py ├── gradio_demo.py ├── mmaudio ├── __init__.py ├── data │ ├── __init__.py │ ├── av_utils.py │ ├── data_setup.py │ ├── eval │ │ ├── __init__.py │ │ ├── audiocaps.py │ │ ├── moviegen.py │ │ └── video_dataset.py │ ├── extracted_audio.py │ ├── extracted_vgg.py │ ├── extraction │ │ ├── __init__.py │ │ ├── vgg_sound.py │ │ └── wav_dataset.py │ ├── mm_dataset.py │ └── utils.py ├── eval_utils.py ├── ext │ ├── __init__.py │ ├── autoencoder │ │ ├── __init__.py │ │ ├── autoencoder.py │ │ ├── edm2_utils.py │ │ ├── vae.py │ │ └── vae_modules.py │ ├── bigvgan │ │ ├── LICENSE │ │ ├── __init__.py │ │ ├── activations.py │ │ ├── alias_free_torch │ │ │ ├── __init__.py │ │ │ ├── act.py │ │ │ ├── filter.py │ │ │ └── resample.py │ │ ├── bigvgan.py │ │ ├── bigvgan_vocoder.yml │ │ ├── env.py │ │ ├── incl_licenses │ │ │ ├── LICENSE_1 │ │ │ ├── LICENSE_2 │ │ │ ├── LICENSE_3 │ │ │ ├── LICENSE_4 │ │ │ └── LICENSE_5 │ │ ├── models.py │ │ └── utils.py │ ├── bigvgan_v2 │ │ ├── LICENSE │ │ ├── __init__.py │ │ ├── activations.py │ │ ├── alias_free_activation │ │ │ ├── cuda │ │ │ │ ├── __init__.py │ │ │ │ ├── activation1d.py │ │ │ │ ├── anti_alias_activation.cpp │ │ │ │ ├── anti_alias_activation_cuda.cu │ │ │ │ ├── compat.h │ │ │ │ ├── load.py │ │ │ │ └── type_shim.h │ │ │ └── torch │ │ │ │ ├── __init__.py │ │ │ │ ├── act.py │ │ │ │ ├── filter.py │ │ │ │ └── resample.py │ │ ├── bigvgan.py │ │ ├── env.py │ │ ├── incl_licenses │ │ │ ├── LICENSE_1 │ │ │ ├── LICENSE_2 │ │ │ ├── LICENSE_3 │ │ │ ├── LICENSE_4 │ │ │ ├── LICENSE_5 │ │ │ ├── LICENSE_6 │ │ │ ├── LICENSE_7 │ │ │ └── LICENSE_8 │ │ └── utils.py │ ├── mel_converter.py │ ├── rotary_embeddings.py │ ├── stft_converter.py │ ├── stft_converter_mel.py │ └── synchformer │ │ ├── LICENSE │ │ ├── __init__.py │ │ ├── divided_224_16x4.yaml │ │ ├── motionformer.py │ │ ├── synchformer.py │ │ ├── utils.py │ │ ├── video_model_builder.py │ │ └── vit_helper.py ├── model │ ├── __init__.py │ ├── embeddings.py │ ├── flow_matching.py │ ├── low_level.py │ ├── networks.py │ ├── sequence_config.py │ ├── transformer_layers.py │ └── utils │ │ ├── __init__.py │ │ ├── distributions.py │ │ ├── features_utils.py │ │ ├── parameter_groups.py │ │ └── sample_utils.py ├── runner.py ├── sample.py └── utils │ ├── __init__.py │ ├── dist_utils.py │ ├── download_utils.py │ ├── email_utils.py │ ├── log_integrator.py │ ├── logger.py │ ├── synthesize_ema.py │ ├── tensor_utils.py │ ├── time_estimator.py │ ├── timezone.py │ └── video_joiner.py ├── pyproject.toml ├── sets ├── vgg-test.tsv ├── vgg-train.tsv └── vgg-val.tsv ├── train.py └── training ├── example_audio.tsv ├── example_audios ├── 00008004.flac └── 00008009.flac ├── example_video.tsv ├── example_videos ├── 0B4dYTMsgHA_000130.mp4 └── F8Zt3mYlOqU_000094.mp4 ├── extract_audio_training_latents.py ├── extract_video_training_latents.py └── partition_clips.py /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/.gitignore -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/README.md -------------------------------------------------------------------------------- /batch_eval.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/batch_eval.py -------------------------------------------------------------------------------- /config/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /config/base_config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/config/base_config.yaml -------------------------------------------------------------------------------- /config/data/base.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/config/data/base.yaml -------------------------------------------------------------------------------- /config/eval_config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/config/eval_config.yaml -------------------------------------------------------------------------------- /config/eval_data/base.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/config/eval_data/base.yaml -------------------------------------------------------------------------------- /config/hydra/job_logging/custom-eval.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/config/hydra/job_logging/custom-eval.yaml -------------------------------------------------------------------------------- /config/hydra/job_logging/custom-no-rank.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/config/hydra/job_logging/custom-no-rank.yaml -------------------------------------------------------------------------------- /config/hydra/job_logging/custom-simplest.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/config/hydra/job_logging/custom-simplest.yaml -------------------------------------------------------------------------------- /config/hydra/job_logging/custom.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/config/hydra/job_logging/custom.yaml -------------------------------------------------------------------------------- /config/train_config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/config/train_config.yaml -------------------------------------------------------------------------------- /demo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/demo.py -------------------------------------------------------------------------------- /docs/EVAL.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/docs/EVAL.md -------------------------------------------------------------------------------- /docs/MODELS.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/docs/MODELS.md -------------------------------------------------------------------------------- /docs/TRAINING.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/docs/TRAINING.md -------------------------------------------------------------------------------- /docs/images/icon.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/docs/images/icon.png -------------------------------------------------------------------------------- /docs/index.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/docs/index.html -------------------------------------------------------------------------------- /docs/style.css: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/docs/style.css -------------------------------------------------------------------------------- /docs/style_videos.css: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/docs/style_videos.css -------------------------------------------------------------------------------- /docs/video_demo.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/docs/video_demo.html -------------------------------------------------------------------------------- /docs/video_gen.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/docs/video_gen.html -------------------------------------------------------------------------------- /docs/video_main.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/docs/video_main.html -------------------------------------------------------------------------------- /docs/video_vgg.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/docs/video_vgg.html -------------------------------------------------------------------------------- /eval_onsets.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/eval_onsets.py -------------------------------------------------------------------------------- /gradio_demo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/gradio_demo.py -------------------------------------------------------------------------------- /mmaudio/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /mmaudio/data/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /mmaudio/data/av_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/data/av_utils.py -------------------------------------------------------------------------------- /mmaudio/data/data_setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/data/data_setup.py -------------------------------------------------------------------------------- /mmaudio/data/eval/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /mmaudio/data/eval/audiocaps.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/data/eval/audiocaps.py -------------------------------------------------------------------------------- /mmaudio/data/eval/moviegen.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/data/eval/moviegen.py -------------------------------------------------------------------------------- /mmaudio/data/eval/video_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/data/eval/video_dataset.py -------------------------------------------------------------------------------- /mmaudio/data/extracted_audio.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/data/extracted_audio.py -------------------------------------------------------------------------------- /mmaudio/data/extracted_vgg.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/data/extracted_vgg.py -------------------------------------------------------------------------------- /mmaudio/data/extraction/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /mmaudio/data/extraction/vgg_sound.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/data/extraction/vgg_sound.py -------------------------------------------------------------------------------- /mmaudio/data/extraction/wav_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/data/extraction/wav_dataset.py -------------------------------------------------------------------------------- /mmaudio/data/mm_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/data/mm_dataset.py -------------------------------------------------------------------------------- /mmaudio/data/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/data/utils.py -------------------------------------------------------------------------------- /mmaudio/eval_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/eval_utils.py -------------------------------------------------------------------------------- /mmaudio/ext/__init__.py: -------------------------------------------------------------------------------- 1 | 2 | -------------------------------------------------------------------------------- /mmaudio/ext/autoencoder/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/ext/autoencoder/__init__.py -------------------------------------------------------------------------------- /mmaudio/ext/autoencoder/autoencoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/ext/autoencoder/autoencoder.py -------------------------------------------------------------------------------- /mmaudio/ext/autoencoder/edm2_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/ext/autoencoder/edm2_utils.py -------------------------------------------------------------------------------- /mmaudio/ext/autoencoder/vae.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/ext/autoencoder/vae.py -------------------------------------------------------------------------------- /mmaudio/ext/autoencoder/vae_modules.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/ext/autoencoder/vae_modules.py -------------------------------------------------------------------------------- /mmaudio/ext/bigvgan/LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/ext/bigvgan/LICENSE -------------------------------------------------------------------------------- /mmaudio/ext/bigvgan/__init__.py: -------------------------------------------------------------------------------- 1 | from .bigvgan import BigVGAN 2 | -------------------------------------------------------------------------------- /mmaudio/ext/bigvgan/activations.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/ext/bigvgan/activations.py -------------------------------------------------------------------------------- /mmaudio/ext/bigvgan/alias_free_torch/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/ext/bigvgan/alias_free_torch/__init__.py -------------------------------------------------------------------------------- /mmaudio/ext/bigvgan/alias_free_torch/act.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/ext/bigvgan/alias_free_torch/act.py -------------------------------------------------------------------------------- /mmaudio/ext/bigvgan/alias_free_torch/filter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/ext/bigvgan/alias_free_torch/filter.py -------------------------------------------------------------------------------- /mmaudio/ext/bigvgan/alias_free_torch/resample.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/ext/bigvgan/alias_free_torch/resample.py -------------------------------------------------------------------------------- /mmaudio/ext/bigvgan/bigvgan.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/ext/bigvgan/bigvgan.py -------------------------------------------------------------------------------- /mmaudio/ext/bigvgan/bigvgan_vocoder.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/ext/bigvgan/bigvgan_vocoder.yml -------------------------------------------------------------------------------- /mmaudio/ext/bigvgan/env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/ext/bigvgan/env.py -------------------------------------------------------------------------------- /mmaudio/ext/bigvgan/incl_licenses/LICENSE_1: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/ext/bigvgan/incl_licenses/LICENSE_1 -------------------------------------------------------------------------------- /mmaudio/ext/bigvgan/incl_licenses/LICENSE_2: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/ext/bigvgan/incl_licenses/LICENSE_2 -------------------------------------------------------------------------------- /mmaudio/ext/bigvgan/incl_licenses/LICENSE_3: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/ext/bigvgan/incl_licenses/LICENSE_3 -------------------------------------------------------------------------------- /mmaudio/ext/bigvgan/incl_licenses/LICENSE_4: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/ext/bigvgan/incl_licenses/LICENSE_4 -------------------------------------------------------------------------------- /mmaudio/ext/bigvgan/incl_licenses/LICENSE_5: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/ext/bigvgan/incl_licenses/LICENSE_5 -------------------------------------------------------------------------------- /mmaudio/ext/bigvgan/models.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/ext/bigvgan/models.py -------------------------------------------------------------------------------- /mmaudio/ext/bigvgan/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/ext/bigvgan/utils.py -------------------------------------------------------------------------------- /mmaudio/ext/bigvgan_v2/LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/ext/bigvgan_v2/LICENSE -------------------------------------------------------------------------------- /mmaudio/ext/bigvgan_v2/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /mmaudio/ext/bigvgan_v2/activations.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/ext/bigvgan_v2/activations.py -------------------------------------------------------------------------------- /mmaudio/ext/bigvgan_v2/alias_free_activation/cuda/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /mmaudio/ext/bigvgan_v2/alias_free_activation/cuda/activation1d.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/ext/bigvgan_v2/alias_free_activation/cuda/activation1d.py -------------------------------------------------------------------------------- /mmaudio/ext/bigvgan_v2/alias_free_activation/cuda/anti_alias_activation.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/ext/bigvgan_v2/alias_free_activation/cuda/anti_alias_activation.cpp -------------------------------------------------------------------------------- /mmaudio/ext/bigvgan_v2/alias_free_activation/cuda/anti_alias_activation_cuda.cu: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/ext/bigvgan_v2/alias_free_activation/cuda/anti_alias_activation_cuda.cu -------------------------------------------------------------------------------- /mmaudio/ext/bigvgan_v2/alias_free_activation/cuda/compat.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/ext/bigvgan_v2/alias_free_activation/cuda/compat.h -------------------------------------------------------------------------------- /mmaudio/ext/bigvgan_v2/alias_free_activation/cuda/load.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/ext/bigvgan_v2/alias_free_activation/cuda/load.py -------------------------------------------------------------------------------- /mmaudio/ext/bigvgan_v2/alias_free_activation/cuda/type_shim.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/ext/bigvgan_v2/alias_free_activation/cuda/type_shim.h -------------------------------------------------------------------------------- /mmaudio/ext/bigvgan_v2/alias_free_activation/torch/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/ext/bigvgan_v2/alias_free_activation/torch/__init__.py -------------------------------------------------------------------------------- /mmaudio/ext/bigvgan_v2/alias_free_activation/torch/act.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/ext/bigvgan_v2/alias_free_activation/torch/act.py -------------------------------------------------------------------------------- /mmaudio/ext/bigvgan_v2/alias_free_activation/torch/filter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/ext/bigvgan_v2/alias_free_activation/torch/filter.py -------------------------------------------------------------------------------- /mmaudio/ext/bigvgan_v2/alias_free_activation/torch/resample.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/ext/bigvgan_v2/alias_free_activation/torch/resample.py -------------------------------------------------------------------------------- /mmaudio/ext/bigvgan_v2/bigvgan.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/ext/bigvgan_v2/bigvgan.py -------------------------------------------------------------------------------- /mmaudio/ext/bigvgan_v2/env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/ext/bigvgan_v2/env.py -------------------------------------------------------------------------------- /mmaudio/ext/bigvgan_v2/incl_licenses/LICENSE_1: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/ext/bigvgan_v2/incl_licenses/LICENSE_1 -------------------------------------------------------------------------------- /mmaudio/ext/bigvgan_v2/incl_licenses/LICENSE_2: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/ext/bigvgan_v2/incl_licenses/LICENSE_2 -------------------------------------------------------------------------------- /mmaudio/ext/bigvgan_v2/incl_licenses/LICENSE_3: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/ext/bigvgan_v2/incl_licenses/LICENSE_3 -------------------------------------------------------------------------------- /mmaudio/ext/bigvgan_v2/incl_licenses/LICENSE_4: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/ext/bigvgan_v2/incl_licenses/LICENSE_4 -------------------------------------------------------------------------------- /mmaudio/ext/bigvgan_v2/incl_licenses/LICENSE_5: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/ext/bigvgan_v2/incl_licenses/LICENSE_5 -------------------------------------------------------------------------------- /mmaudio/ext/bigvgan_v2/incl_licenses/LICENSE_6: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/ext/bigvgan_v2/incl_licenses/LICENSE_6 -------------------------------------------------------------------------------- /mmaudio/ext/bigvgan_v2/incl_licenses/LICENSE_7: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/ext/bigvgan_v2/incl_licenses/LICENSE_7 -------------------------------------------------------------------------------- /mmaudio/ext/bigvgan_v2/incl_licenses/LICENSE_8: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/ext/bigvgan_v2/incl_licenses/LICENSE_8 -------------------------------------------------------------------------------- /mmaudio/ext/bigvgan_v2/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/ext/bigvgan_v2/utils.py -------------------------------------------------------------------------------- /mmaudio/ext/mel_converter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/ext/mel_converter.py -------------------------------------------------------------------------------- /mmaudio/ext/rotary_embeddings.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/ext/rotary_embeddings.py -------------------------------------------------------------------------------- /mmaudio/ext/stft_converter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/ext/stft_converter.py -------------------------------------------------------------------------------- /mmaudio/ext/stft_converter_mel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/ext/stft_converter_mel.py -------------------------------------------------------------------------------- /mmaudio/ext/synchformer/LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/ext/synchformer/LICENSE -------------------------------------------------------------------------------- /mmaudio/ext/synchformer/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/ext/synchformer/__init__.py -------------------------------------------------------------------------------- /mmaudio/ext/synchformer/divided_224_16x4.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/ext/synchformer/divided_224_16x4.yaml -------------------------------------------------------------------------------- /mmaudio/ext/synchformer/motionformer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/ext/synchformer/motionformer.py -------------------------------------------------------------------------------- /mmaudio/ext/synchformer/synchformer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/ext/synchformer/synchformer.py -------------------------------------------------------------------------------- /mmaudio/ext/synchformer/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/ext/synchformer/utils.py -------------------------------------------------------------------------------- /mmaudio/ext/synchformer/video_model_builder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/ext/synchformer/video_model_builder.py -------------------------------------------------------------------------------- /mmaudio/ext/synchformer/vit_helper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/ext/synchformer/vit_helper.py -------------------------------------------------------------------------------- /mmaudio/model/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /mmaudio/model/embeddings.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/model/embeddings.py -------------------------------------------------------------------------------- /mmaudio/model/flow_matching.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/model/flow_matching.py -------------------------------------------------------------------------------- /mmaudio/model/low_level.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/model/low_level.py -------------------------------------------------------------------------------- /mmaudio/model/networks.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/model/networks.py -------------------------------------------------------------------------------- /mmaudio/model/sequence_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/model/sequence_config.py -------------------------------------------------------------------------------- /mmaudio/model/transformer_layers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/model/transformer_layers.py -------------------------------------------------------------------------------- /mmaudio/model/utils/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /mmaudio/model/utils/distributions.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/model/utils/distributions.py -------------------------------------------------------------------------------- /mmaudio/model/utils/features_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/model/utils/features_utils.py -------------------------------------------------------------------------------- /mmaudio/model/utils/parameter_groups.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/model/utils/parameter_groups.py -------------------------------------------------------------------------------- /mmaudio/model/utils/sample_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/model/utils/sample_utils.py -------------------------------------------------------------------------------- /mmaudio/runner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/runner.py -------------------------------------------------------------------------------- /mmaudio/sample.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/sample.py -------------------------------------------------------------------------------- /mmaudio/utils/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /mmaudio/utils/dist_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/utils/dist_utils.py -------------------------------------------------------------------------------- /mmaudio/utils/download_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/utils/download_utils.py -------------------------------------------------------------------------------- /mmaudio/utils/email_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/utils/email_utils.py -------------------------------------------------------------------------------- /mmaudio/utils/log_integrator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/utils/log_integrator.py -------------------------------------------------------------------------------- /mmaudio/utils/logger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/utils/logger.py -------------------------------------------------------------------------------- /mmaudio/utils/synthesize_ema.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/utils/synthesize_ema.py -------------------------------------------------------------------------------- /mmaudio/utils/tensor_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/utils/tensor_utils.py -------------------------------------------------------------------------------- /mmaudio/utils/time_estimator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/utils/time_estimator.py -------------------------------------------------------------------------------- /mmaudio/utils/timezone.py: -------------------------------------------------------------------------------- 1 | my_timezone = 'US/Central' 2 | -------------------------------------------------------------------------------- /mmaudio/utils/video_joiner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/mmaudio/utils/video_joiner.py -------------------------------------------------------------------------------- /pyproject.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/pyproject.toml -------------------------------------------------------------------------------- /sets/vgg-test.tsv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/sets/vgg-test.tsv -------------------------------------------------------------------------------- /sets/vgg-train.tsv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/sets/vgg-train.tsv -------------------------------------------------------------------------------- /sets/vgg-val.tsv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/sets/vgg-val.tsv -------------------------------------------------------------------------------- /train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/train.py -------------------------------------------------------------------------------- /training/example_audio.tsv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/training/example_audio.tsv -------------------------------------------------------------------------------- /training/example_audios/00008004.flac: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/training/example_audios/00008004.flac -------------------------------------------------------------------------------- /training/example_audios/00008009.flac: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/training/example_audios/00008009.flac -------------------------------------------------------------------------------- /training/example_video.tsv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/training/example_video.tsv -------------------------------------------------------------------------------- /training/example_videos/0B4dYTMsgHA_000130.mp4: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/training/example_videos/0B4dYTMsgHA_000130.mp4 -------------------------------------------------------------------------------- /training/example_videos/F8Zt3mYlOqU_000094.mp4: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/training/example_videos/F8Zt3mYlOqU_000094.mp4 -------------------------------------------------------------------------------- /training/extract_audio_training_latents.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/training/extract_audio_training_latents.py -------------------------------------------------------------------------------- /training/extract_video_training_latents.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/training/extract_video_training_latents.py -------------------------------------------------------------------------------- /training/partition_clips.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hkchengrex/MMAudio/HEAD/training/partition_clips.py --------------------------------------------------------------------------------