├── .gitignore ├── README.md ├── config_axolotl └── full_finetune.yml ├── download_ljspeech.sh ├── requirement.txt ├── sparktts ├── models │ ├── audio_tokenizer.py │ └── bicodec.py ├── modules │ ├── blocks │ │ ├── layers.py │ │ ├── samper.py │ │ └── vocos.py │ ├── encoder_decoder │ │ ├── feat_decoder.py │ │ ├── feat_encoder.py │ │ └── wave_generator.py │ ├── fsq │ │ ├── finite_scalar_quantization.py │ │ └── residual_fsq.py │ ├── speaker │ │ ├── ecapa_tdnn.py │ │ ├── perceiver_encoder.py │ │ ├── pooling_layers.py │ │ └── speaker_encoder.py │ └── vq │ │ └── factorized_vector_quantize.py └── utils │ ├── __init__.py │ ├── audio.py │ └── file.py └── src ├── download_pretrain.py └── process_data.py /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tuanh123789/Spark-TTS-finetune/HEAD/.gitignore -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tuanh123789/Spark-TTS-finetune/HEAD/README.md -------------------------------------------------------------------------------- /config_axolotl/full_finetune.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tuanh123789/Spark-TTS-finetune/HEAD/config_axolotl/full_finetune.yml -------------------------------------------------------------------------------- /download_ljspeech.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tuanh123789/Spark-TTS-finetune/HEAD/download_ljspeech.sh -------------------------------------------------------------------------------- /requirement.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tuanh123789/Spark-TTS-finetune/HEAD/requirement.txt -------------------------------------------------------------------------------- /sparktts/models/audio_tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tuanh123789/Spark-TTS-finetune/HEAD/sparktts/models/audio_tokenizer.py -------------------------------------------------------------------------------- /sparktts/models/bicodec.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tuanh123789/Spark-TTS-finetune/HEAD/sparktts/models/bicodec.py -------------------------------------------------------------------------------- /sparktts/modules/blocks/layers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tuanh123789/Spark-TTS-finetune/HEAD/sparktts/modules/blocks/layers.py -------------------------------------------------------------------------------- /sparktts/modules/blocks/samper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tuanh123789/Spark-TTS-finetune/HEAD/sparktts/modules/blocks/samper.py -------------------------------------------------------------------------------- /sparktts/modules/blocks/vocos.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tuanh123789/Spark-TTS-finetune/HEAD/sparktts/modules/blocks/vocos.py -------------------------------------------------------------------------------- /sparktts/modules/encoder_decoder/feat_decoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tuanh123789/Spark-TTS-finetune/HEAD/sparktts/modules/encoder_decoder/feat_decoder.py -------------------------------------------------------------------------------- /sparktts/modules/encoder_decoder/feat_encoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tuanh123789/Spark-TTS-finetune/HEAD/sparktts/modules/encoder_decoder/feat_encoder.py -------------------------------------------------------------------------------- /sparktts/modules/encoder_decoder/wave_generator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tuanh123789/Spark-TTS-finetune/HEAD/sparktts/modules/encoder_decoder/wave_generator.py -------------------------------------------------------------------------------- /sparktts/modules/fsq/finite_scalar_quantization.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tuanh123789/Spark-TTS-finetune/HEAD/sparktts/modules/fsq/finite_scalar_quantization.py -------------------------------------------------------------------------------- /sparktts/modules/fsq/residual_fsq.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tuanh123789/Spark-TTS-finetune/HEAD/sparktts/modules/fsq/residual_fsq.py -------------------------------------------------------------------------------- /sparktts/modules/speaker/ecapa_tdnn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tuanh123789/Spark-TTS-finetune/HEAD/sparktts/modules/speaker/ecapa_tdnn.py -------------------------------------------------------------------------------- /sparktts/modules/speaker/perceiver_encoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tuanh123789/Spark-TTS-finetune/HEAD/sparktts/modules/speaker/perceiver_encoder.py -------------------------------------------------------------------------------- /sparktts/modules/speaker/pooling_layers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tuanh123789/Spark-TTS-finetune/HEAD/sparktts/modules/speaker/pooling_layers.py -------------------------------------------------------------------------------- /sparktts/modules/speaker/speaker_encoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tuanh123789/Spark-TTS-finetune/HEAD/sparktts/modules/speaker/speaker_encoder.py -------------------------------------------------------------------------------- /sparktts/modules/vq/factorized_vector_quantize.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tuanh123789/Spark-TTS-finetune/HEAD/sparktts/modules/vq/factorized_vector_quantize.py -------------------------------------------------------------------------------- /sparktts/utils/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /sparktts/utils/audio.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tuanh123789/Spark-TTS-finetune/HEAD/sparktts/utils/audio.py -------------------------------------------------------------------------------- /sparktts/utils/file.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tuanh123789/Spark-TTS-finetune/HEAD/sparktts/utils/file.py -------------------------------------------------------------------------------- /src/download_pretrain.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tuanh123789/Spark-TTS-finetune/HEAD/src/download_pretrain.py -------------------------------------------------------------------------------- /src/process_data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tuanh123789/Spark-TTS-finetune/HEAD/src/process_data.py --------------------------------------------------------------------------------