├── .github └── FUNDING.yml ├── .gitignore ├── .pre-commit-config.yaml ├── LICENSE ├── MANIFEST.in ├── README.md ├── assets └── logo.png ├── notebook ├── inference.ipynb └── train.ipynb ├── requirements.txt ├── setup.cfg ├── setup.py └── speechplus ├── __init__.py ├── config ├── config.json ├── data_config.json └── ds_config.json ├── data ├── dataset_speech.py └── preprocessing.py ├── inference.py ├── model ├── __init__.py └── wav_tokenizer │ ├── __init__.py │ ├── audio_codec.py │ ├── decoder │ ├── __init__.py │ ├── dataset.py │ ├── discriminator_dac.py │ ├── discriminators.py │ ├── experiment.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 │ ├── distrib.py │ ├── model.py │ ├── modules │ │ ├── __init__.py │ │ ├── conv.py │ │ ├── lstm.py │ │ ├── norm.py │ │ ├── seanet.py │ │ └── transformer.py │ ├── msstftd.py │ ├── quantization │ │ ├── __init__.py │ │ ├── ac.py │ │ ├── core_vq.py │ │ └── vq.py │ └── utils.py │ └── model.py ├── multi_train.py └── train.py /.github/FUNDING.yml: -------------------------------------------------------------------------------- 1 | kadirnar 2 | -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Vyvo-Labs/SpeechPlus/HEAD/.gitignore -------------------------------------------------------------------------------- /.pre-commit-config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Vyvo-Labs/SpeechPlus/HEAD/.pre-commit-config.yaml -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Vyvo-Labs/SpeechPlus/HEAD/LICENSE -------------------------------------------------------------------------------- /MANIFEST.in: -------------------------------------------------------------------------------- 1 | include requirements.txt 2 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Vyvo-Labs/SpeechPlus/HEAD/README.md -------------------------------------------------------------------------------- /assets/logo.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Vyvo-Labs/SpeechPlus/HEAD/assets/logo.png -------------------------------------------------------------------------------- /notebook/inference.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Vyvo-Labs/SpeechPlus/HEAD/notebook/inference.ipynb -------------------------------------------------------------------------------- /notebook/train.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Vyvo-Labs/SpeechPlus/HEAD/notebook/train.ipynb -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Vyvo-Labs/SpeechPlus/HEAD/requirements.txt -------------------------------------------------------------------------------- /setup.cfg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Vyvo-Labs/SpeechPlus/HEAD/setup.cfg -------------------------------------------------------------------------------- /setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Vyvo-Labs/SpeechPlus/HEAD/setup.py -------------------------------------------------------------------------------- /speechplus/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Vyvo-Labs/SpeechPlus/HEAD/speechplus/__init__.py -------------------------------------------------------------------------------- /speechplus/config/config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Vyvo-Labs/SpeechPlus/HEAD/speechplus/config/config.json -------------------------------------------------------------------------------- /speechplus/config/data_config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Vyvo-Labs/SpeechPlus/HEAD/speechplus/config/data_config.json -------------------------------------------------------------------------------- /speechplus/config/ds_config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Vyvo-Labs/SpeechPlus/HEAD/speechplus/config/ds_config.json -------------------------------------------------------------------------------- /speechplus/data/dataset_speech.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Vyvo-Labs/SpeechPlus/HEAD/speechplus/data/dataset_speech.py -------------------------------------------------------------------------------- /speechplus/data/preprocessing.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Vyvo-Labs/SpeechPlus/HEAD/speechplus/data/preprocessing.py -------------------------------------------------------------------------------- /speechplus/inference.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Vyvo-Labs/SpeechPlus/HEAD/speechplus/inference.py -------------------------------------------------------------------------------- /speechplus/model/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /speechplus/model/wav_tokenizer/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Vyvo-Labs/SpeechPlus/HEAD/speechplus/model/wav_tokenizer/__init__.py -------------------------------------------------------------------------------- /speechplus/model/wav_tokenizer/audio_codec.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Vyvo-Labs/SpeechPlus/HEAD/speechplus/model/wav_tokenizer/audio_codec.py -------------------------------------------------------------------------------- /speechplus/model/wav_tokenizer/decoder/__init__.py: -------------------------------------------------------------------------------- 1 | from decoder.pretrained import WavTokenizer 2 | 3 | __version__ = "0.0.3" 4 | -------------------------------------------------------------------------------- /speechplus/model/wav_tokenizer/decoder/dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Vyvo-Labs/SpeechPlus/HEAD/speechplus/model/wav_tokenizer/decoder/dataset.py -------------------------------------------------------------------------------- /speechplus/model/wav_tokenizer/decoder/discriminator_dac.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Vyvo-Labs/SpeechPlus/HEAD/speechplus/model/wav_tokenizer/decoder/discriminator_dac.py -------------------------------------------------------------------------------- /speechplus/model/wav_tokenizer/decoder/discriminators.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Vyvo-Labs/SpeechPlus/HEAD/speechplus/model/wav_tokenizer/decoder/discriminators.py -------------------------------------------------------------------------------- /speechplus/model/wav_tokenizer/decoder/experiment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Vyvo-Labs/SpeechPlus/HEAD/speechplus/model/wav_tokenizer/decoder/experiment.py -------------------------------------------------------------------------------- /speechplus/model/wav_tokenizer/decoder/feature_extractors.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Vyvo-Labs/SpeechPlus/HEAD/speechplus/model/wav_tokenizer/decoder/feature_extractors.py -------------------------------------------------------------------------------- /speechplus/model/wav_tokenizer/decoder/heads.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Vyvo-Labs/SpeechPlus/HEAD/speechplus/model/wav_tokenizer/decoder/heads.py -------------------------------------------------------------------------------- /speechplus/model/wav_tokenizer/decoder/helpers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Vyvo-Labs/SpeechPlus/HEAD/speechplus/model/wav_tokenizer/decoder/helpers.py -------------------------------------------------------------------------------- /speechplus/model/wav_tokenizer/decoder/loss.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Vyvo-Labs/SpeechPlus/HEAD/speechplus/model/wav_tokenizer/decoder/loss.py -------------------------------------------------------------------------------- /speechplus/model/wav_tokenizer/decoder/models.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Vyvo-Labs/SpeechPlus/HEAD/speechplus/model/wav_tokenizer/decoder/models.py -------------------------------------------------------------------------------- /speechplus/model/wav_tokenizer/decoder/modules.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Vyvo-Labs/SpeechPlus/HEAD/speechplus/model/wav_tokenizer/decoder/modules.py -------------------------------------------------------------------------------- /speechplus/model/wav_tokenizer/decoder/pretrained.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Vyvo-Labs/SpeechPlus/HEAD/speechplus/model/wav_tokenizer/decoder/pretrained.py -------------------------------------------------------------------------------- /speechplus/model/wav_tokenizer/decoder/pretrained_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Vyvo-Labs/SpeechPlus/HEAD/speechplus/model/wav_tokenizer/decoder/pretrained_model.py -------------------------------------------------------------------------------- /speechplus/model/wav_tokenizer/decoder/spectral_ops.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Vyvo-Labs/SpeechPlus/HEAD/speechplus/model/wav_tokenizer/decoder/spectral_ops.py -------------------------------------------------------------------------------- /speechplus/model/wav_tokenizer/encoder/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Vyvo-Labs/SpeechPlus/HEAD/speechplus/model/wav_tokenizer/encoder/__init__.py -------------------------------------------------------------------------------- /speechplus/model/wav_tokenizer/encoder/distrib.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Vyvo-Labs/SpeechPlus/HEAD/speechplus/model/wav_tokenizer/encoder/distrib.py -------------------------------------------------------------------------------- /speechplus/model/wav_tokenizer/encoder/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Vyvo-Labs/SpeechPlus/HEAD/speechplus/model/wav_tokenizer/encoder/model.py -------------------------------------------------------------------------------- /speechplus/model/wav_tokenizer/encoder/modules/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /speechplus/model/wav_tokenizer/encoder/modules/conv.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Vyvo-Labs/SpeechPlus/HEAD/speechplus/model/wav_tokenizer/encoder/modules/conv.py -------------------------------------------------------------------------------- /speechplus/model/wav_tokenizer/encoder/modules/lstm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Vyvo-Labs/SpeechPlus/HEAD/speechplus/model/wav_tokenizer/encoder/modules/lstm.py -------------------------------------------------------------------------------- /speechplus/model/wav_tokenizer/encoder/modules/norm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Vyvo-Labs/SpeechPlus/HEAD/speechplus/model/wav_tokenizer/encoder/modules/norm.py -------------------------------------------------------------------------------- /speechplus/model/wav_tokenizer/encoder/modules/seanet.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Vyvo-Labs/SpeechPlus/HEAD/speechplus/model/wav_tokenizer/encoder/modules/seanet.py -------------------------------------------------------------------------------- /speechplus/model/wav_tokenizer/encoder/modules/transformer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Vyvo-Labs/SpeechPlus/HEAD/speechplus/model/wav_tokenizer/encoder/modules/transformer.py -------------------------------------------------------------------------------- /speechplus/model/wav_tokenizer/encoder/msstftd.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Vyvo-Labs/SpeechPlus/HEAD/speechplus/model/wav_tokenizer/encoder/msstftd.py -------------------------------------------------------------------------------- /speechplus/model/wav_tokenizer/encoder/quantization/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Vyvo-Labs/SpeechPlus/HEAD/speechplus/model/wav_tokenizer/encoder/quantization/__init__.py -------------------------------------------------------------------------------- /speechplus/model/wav_tokenizer/encoder/quantization/ac.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Vyvo-Labs/SpeechPlus/HEAD/speechplus/model/wav_tokenizer/encoder/quantization/ac.py -------------------------------------------------------------------------------- /speechplus/model/wav_tokenizer/encoder/quantization/core_vq.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Vyvo-Labs/SpeechPlus/HEAD/speechplus/model/wav_tokenizer/encoder/quantization/core_vq.py -------------------------------------------------------------------------------- /speechplus/model/wav_tokenizer/encoder/quantization/vq.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Vyvo-Labs/SpeechPlus/HEAD/speechplus/model/wav_tokenizer/encoder/quantization/vq.py -------------------------------------------------------------------------------- /speechplus/model/wav_tokenizer/encoder/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Vyvo-Labs/SpeechPlus/HEAD/speechplus/model/wav_tokenizer/encoder/utils.py -------------------------------------------------------------------------------- /speechplus/model/wav_tokenizer/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Vyvo-Labs/SpeechPlus/HEAD/speechplus/model/wav_tokenizer/model.py -------------------------------------------------------------------------------- /speechplus/multi_train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Vyvo-Labs/SpeechPlus/HEAD/speechplus/multi_train.py -------------------------------------------------------------------------------- /speechplus/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Vyvo-Labs/SpeechPlus/HEAD/speechplus/train.py --------------------------------------------------------------------------------