├── README.md ├── comparison table.png ├── configs ├── unicodec_frame75_10s_nq1_code16384_dim512_acousitic.yaml ├── unicodec_frame75_10s_nq1_code16384_dim512_finetune.yaml └── unicodec_frame75_10s_nq1_code16384_dim512_semantic.yaml ├── decoder ├── __init__.py ├── dataset.py ├── discriminator_dac.py ├── discriminators.py ├── experiment.py ├── experiment_contrastive.py ├── feature_extractors.py ├── heads.py ├── helpers.py ├── loss.py ├── models.py ├── modules.py ├── pretrained.py ├── pretrained_model.py └── spectral_ops.py ├── encoder ├── __init__.py ├── compile.py ├── distrib.py ├── model.py ├── modules │ ├── __init__.py │ ├── conv.py │ ├── gating.py │ ├── lstm.py │ ├── mimi_transformer.py │ ├── norm.py │ ├── resample.py │ ├── rope.py │ ├── seanet.py │ ├── streaming.py │ └── transformer.py ├── msstftd.py ├── quantization │ ├── __init__.py │ ├── __pycache__ │ │ ├── .nfs0000000054472a2c00000001 │ │ ├── __init__.cpython-310.pyc │ │ ├── __init__.cpython-38.pyc │ │ ├── __init__.cpython-39.pyc │ │ ├── core_vq.cpython-310.pyc │ │ ├── core_vq.cpython-38.pyc │ │ ├── core_vq.cpython-39.pyc │ │ ├── simvq.cpython-39.pyc │ │ ├── simvq_moe.cpython-39.pyc │ │ ├── vq.cpython-310.pyc │ │ ├── vq.cpython-38.pyc │ │ └── vq.cpython-39.pyc │ ├── ac.py │ ├── core_vq.py │ ├── simvq_moe.py │ └── vq.py └── utils.py ├── infer_audio.py ├── main result.png ├── overview.png ├── requirements.txt └── train.py /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Jiang-Yidi/UniCodec/HEAD/README.md -------------------------------------------------------------------------------- /comparison table.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Jiang-Yidi/UniCodec/HEAD/comparison table.png -------------------------------------------------------------------------------- /configs/unicodec_frame75_10s_nq1_code16384_dim512_acousitic.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Jiang-Yidi/UniCodec/HEAD/configs/unicodec_frame75_10s_nq1_code16384_dim512_acousitic.yaml -------------------------------------------------------------------------------- /configs/unicodec_frame75_10s_nq1_code16384_dim512_finetune.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Jiang-Yidi/UniCodec/HEAD/configs/unicodec_frame75_10s_nq1_code16384_dim512_finetune.yaml -------------------------------------------------------------------------------- /configs/unicodec_frame75_10s_nq1_code16384_dim512_semantic.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Jiang-Yidi/UniCodec/HEAD/configs/unicodec_frame75_10s_nq1_code16384_dim512_semantic.yaml -------------------------------------------------------------------------------- /decoder/__init__.py: -------------------------------------------------------------------------------- 1 | from vocos.pretrained import Vocos 2 | 3 | 4 | __version__ = "0.0.3" 5 | -------------------------------------------------------------------------------- /decoder/dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Jiang-Yidi/UniCodec/HEAD/decoder/dataset.py -------------------------------------------------------------------------------- /decoder/discriminator_dac.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Jiang-Yidi/UniCodec/HEAD/decoder/discriminator_dac.py -------------------------------------------------------------------------------- /decoder/discriminators.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Jiang-Yidi/UniCodec/HEAD/decoder/discriminators.py -------------------------------------------------------------------------------- /decoder/experiment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Jiang-Yidi/UniCodec/HEAD/decoder/experiment.py -------------------------------------------------------------------------------- /decoder/experiment_contrastive.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Jiang-Yidi/UniCodec/HEAD/decoder/experiment_contrastive.py -------------------------------------------------------------------------------- /decoder/feature_extractors.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Jiang-Yidi/UniCodec/HEAD/decoder/feature_extractors.py -------------------------------------------------------------------------------- /decoder/heads.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Jiang-Yidi/UniCodec/HEAD/decoder/heads.py -------------------------------------------------------------------------------- /decoder/helpers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Jiang-Yidi/UniCodec/HEAD/decoder/helpers.py -------------------------------------------------------------------------------- /decoder/loss.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Jiang-Yidi/UniCodec/HEAD/decoder/loss.py -------------------------------------------------------------------------------- /decoder/models.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Jiang-Yidi/UniCodec/HEAD/decoder/models.py -------------------------------------------------------------------------------- /decoder/modules.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Jiang-Yidi/UniCodec/HEAD/decoder/modules.py -------------------------------------------------------------------------------- /decoder/pretrained.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Jiang-Yidi/UniCodec/HEAD/decoder/pretrained.py -------------------------------------------------------------------------------- /decoder/pretrained_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Jiang-Yidi/UniCodec/HEAD/decoder/pretrained_model.py -------------------------------------------------------------------------------- /decoder/spectral_ops.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Jiang-Yidi/UniCodec/HEAD/decoder/spectral_ops.py -------------------------------------------------------------------------------- /encoder/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Jiang-Yidi/UniCodec/HEAD/encoder/__init__.py -------------------------------------------------------------------------------- /encoder/compile.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Jiang-Yidi/UniCodec/HEAD/encoder/compile.py -------------------------------------------------------------------------------- /encoder/distrib.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Jiang-Yidi/UniCodec/HEAD/encoder/distrib.py -------------------------------------------------------------------------------- /encoder/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Jiang-Yidi/UniCodec/HEAD/encoder/model.py -------------------------------------------------------------------------------- /encoder/modules/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Jiang-Yidi/UniCodec/HEAD/encoder/modules/__init__.py -------------------------------------------------------------------------------- /encoder/modules/conv.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Jiang-Yidi/UniCodec/HEAD/encoder/modules/conv.py -------------------------------------------------------------------------------- /encoder/modules/gating.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Jiang-Yidi/UniCodec/HEAD/encoder/modules/gating.py -------------------------------------------------------------------------------- /encoder/modules/lstm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Jiang-Yidi/UniCodec/HEAD/encoder/modules/lstm.py -------------------------------------------------------------------------------- /encoder/modules/mimi_transformer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Jiang-Yidi/UniCodec/HEAD/encoder/modules/mimi_transformer.py -------------------------------------------------------------------------------- /encoder/modules/norm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Jiang-Yidi/UniCodec/HEAD/encoder/modules/norm.py -------------------------------------------------------------------------------- /encoder/modules/resample.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Jiang-Yidi/UniCodec/HEAD/encoder/modules/resample.py -------------------------------------------------------------------------------- /encoder/modules/rope.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Jiang-Yidi/UniCodec/HEAD/encoder/modules/rope.py -------------------------------------------------------------------------------- /encoder/modules/seanet.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Jiang-Yidi/UniCodec/HEAD/encoder/modules/seanet.py -------------------------------------------------------------------------------- /encoder/modules/streaming.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Jiang-Yidi/UniCodec/HEAD/encoder/modules/streaming.py -------------------------------------------------------------------------------- /encoder/modules/transformer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Jiang-Yidi/UniCodec/HEAD/encoder/modules/transformer.py -------------------------------------------------------------------------------- /encoder/msstftd.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Jiang-Yidi/UniCodec/HEAD/encoder/msstftd.py -------------------------------------------------------------------------------- /encoder/quantization/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Jiang-Yidi/UniCodec/HEAD/encoder/quantization/__init__.py -------------------------------------------------------------------------------- /encoder/quantization/__pycache__/.nfs0000000054472a2c00000001: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Jiang-Yidi/UniCodec/HEAD/encoder/quantization/__pycache__/.nfs0000000054472a2c00000001 -------------------------------------------------------------------------------- /encoder/quantization/__pycache__/__init__.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Jiang-Yidi/UniCodec/HEAD/encoder/quantization/__pycache__/__init__.cpython-310.pyc -------------------------------------------------------------------------------- /encoder/quantization/__pycache__/__init__.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Jiang-Yidi/UniCodec/HEAD/encoder/quantization/__pycache__/__init__.cpython-38.pyc -------------------------------------------------------------------------------- /encoder/quantization/__pycache__/__init__.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Jiang-Yidi/UniCodec/HEAD/encoder/quantization/__pycache__/__init__.cpython-39.pyc -------------------------------------------------------------------------------- /encoder/quantization/__pycache__/core_vq.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Jiang-Yidi/UniCodec/HEAD/encoder/quantization/__pycache__/core_vq.cpython-310.pyc -------------------------------------------------------------------------------- /encoder/quantization/__pycache__/core_vq.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Jiang-Yidi/UniCodec/HEAD/encoder/quantization/__pycache__/core_vq.cpython-38.pyc -------------------------------------------------------------------------------- /encoder/quantization/__pycache__/core_vq.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Jiang-Yidi/UniCodec/HEAD/encoder/quantization/__pycache__/core_vq.cpython-39.pyc -------------------------------------------------------------------------------- /encoder/quantization/__pycache__/simvq.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Jiang-Yidi/UniCodec/HEAD/encoder/quantization/__pycache__/simvq.cpython-39.pyc -------------------------------------------------------------------------------- /encoder/quantization/__pycache__/simvq_moe.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Jiang-Yidi/UniCodec/HEAD/encoder/quantization/__pycache__/simvq_moe.cpython-39.pyc -------------------------------------------------------------------------------- /encoder/quantization/__pycache__/vq.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Jiang-Yidi/UniCodec/HEAD/encoder/quantization/__pycache__/vq.cpython-310.pyc -------------------------------------------------------------------------------- /encoder/quantization/__pycache__/vq.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Jiang-Yidi/UniCodec/HEAD/encoder/quantization/__pycache__/vq.cpython-38.pyc -------------------------------------------------------------------------------- /encoder/quantization/__pycache__/vq.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Jiang-Yidi/UniCodec/HEAD/encoder/quantization/__pycache__/vq.cpython-39.pyc -------------------------------------------------------------------------------- /encoder/quantization/ac.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Jiang-Yidi/UniCodec/HEAD/encoder/quantization/ac.py -------------------------------------------------------------------------------- /encoder/quantization/core_vq.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Jiang-Yidi/UniCodec/HEAD/encoder/quantization/core_vq.py -------------------------------------------------------------------------------- /encoder/quantization/simvq_moe.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Jiang-Yidi/UniCodec/HEAD/encoder/quantization/simvq_moe.py -------------------------------------------------------------------------------- /encoder/quantization/vq.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Jiang-Yidi/UniCodec/HEAD/encoder/quantization/vq.py -------------------------------------------------------------------------------- /encoder/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Jiang-Yidi/UniCodec/HEAD/encoder/utils.py -------------------------------------------------------------------------------- /infer_audio.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Jiang-Yidi/UniCodec/HEAD/infer_audio.py -------------------------------------------------------------------------------- /main result.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Jiang-Yidi/UniCodec/HEAD/main result.png -------------------------------------------------------------------------------- /overview.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Jiang-Yidi/UniCodec/HEAD/overview.png -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Jiang-Yidi/UniCodec/HEAD/requirements.txt -------------------------------------------------------------------------------- /train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Jiang-Yidi/UniCodec/HEAD/train.py --------------------------------------------------------------------------------