README.md
pyproject.toml
src/cosyvoice/__init__.py
src/cosyvoice/bin/average_model.py
src/cosyvoice/bin/export_jit.py
src/cosyvoice/bin/export_onnx.py
src/cosyvoice/bin/inference_deprecated.py
src/cosyvoice/bin/train.py
src/cosyvoice/cli/__init__.py
src/cosyvoice/cli/cosyvoice.py
src/cosyvoice/cli/frontend.py
src/cosyvoice/cli/model.py
src/cosyvoice/dataset/__init__.py
src/cosyvoice/dataset/dataset.py
src/cosyvoice/dataset/processor.py
src/cosyvoice/flow/decoder.py
src/cosyvoice/flow/flow.py
src/cosyvoice/flow/flow_matching.py
src/cosyvoice/flow/length_regulator.py
src/cosyvoice/hifigan/discriminator.py
src/cosyvoice/hifigan/f0_predictor.py
src/cosyvoice/hifigan/generator.py
src/cosyvoice/hifigan/hifigan.py
src/cosyvoice/llm/llm.py
src/cosyvoice/tokenizer/tokenizer.py
src/cosyvoice/tokenizer/assets/multilingual_zh_ja_yue_char_del.tiktoken
src/cosyvoice/transformer/__init__.py
src/cosyvoice/transformer/activation.py
src/cosyvoice/transformer/attention.py
src/cosyvoice/transformer/convolution.py
src/cosyvoice/transformer/decoder.py
src/cosyvoice/transformer/decoder_layer.py
src/cosyvoice/transformer/embedding.py
src/cosyvoice/transformer/encoder.py
src/cosyvoice/transformer/encoder_layer.py
src/cosyvoice/transformer/label_smoothing_loss.py
src/cosyvoice/transformer/positionwise_feed_forward.py
src/cosyvoice/transformer/subsampling.py
src/cosyvoice/transformer/upsample_encoder.py
src/cosyvoice/utils/__init__.py
src/cosyvoice/utils/class_utils.py
src/cosyvoice/utils/common.py
src/cosyvoice/utils/executor.py
src/cosyvoice/utils/file_utils.py
src/cosyvoice/utils/frontend_utils.py
src/cosyvoice/utils/losses.py
src/cosyvoice/utils/mask.py
src/cosyvoice/utils/scheduler.py
src/cosyvoice/utils/train_utils.py
src/cosyvoice/vllm/cosyvoice2.py
src/matcha/__init__.py
src/matcha/app.py
src/matcha/cli.py
src/matcha/train.py
src/matcha/hifigan/__init__.py
src/matcha/hifigan/config.py
src/matcha/hifigan/denoiser.py
src/matcha/hifigan/env.py
src/matcha/hifigan/meldataset.py
src/matcha/hifigan/models.py
src/matcha/hifigan/xutils.py
src/matcha/models/__init__.py
src/matcha/models/baselightningmodule.py
src/matcha/models/matcha_tts.py
src/matcha/models/components/__init__.py
src/matcha/models/components/decoder.py
src/matcha/models/components/flow_matching.py
src/matcha/models/components/text_encoder.py
src/matcha/models/components/transformer.py
src/matcha/onnx/__init__.py
src/matcha/onnx/export.py
src/matcha/onnx/infer.py
src/matcha/text/__init__.py
src/matcha/text/cleaners.py
src/matcha/text/numbers.py
src/matcha/text/symbols.py
src/matcha/utils/__init__.py
src/matcha/utils/audio.py
src/matcha/utils/generate_data_statistics.py
src/matcha/utils/instantiators.py
src/matcha/utils/logging_utils.py
src/matcha/utils/model.py
src/matcha/utils/pylogger.py
src/matcha/utils/rich_utils.py
src/matcha/utils/utils.py
src/matcha/utils/monotonic_align/__init__.py
src/matcha/utils/monotonic_align/setup.py
src/minicpmo/__init__.py
src/minicpmo/utils.py
src/minicpmo/version.py
src/minicpmo.egg-info/PKG-INFO
src/minicpmo.egg-info/SOURCES.txt
src/minicpmo.egg-info/dependency_links.txt
src/minicpmo.egg-info/requires.txt
src/minicpmo.egg-info/top_level.txt
src/s3tokenizer/__init__.py
src/s3tokenizer/cli.py
src/s3tokenizer/model.py
src/s3tokenizer/model_v2.py
src/s3tokenizer/utils.py
src/s3tokenizer/assets/BAC009S0764W0121.wav
src/s3tokenizer/assets/BAC009S0764W0122.wav
src/s3tokenizer/assets/mel_filters.npz
src/stepaudio2/__init__.py
src/stepaudio2/stepaudio2.py
src/stepaudio2/token2wav.py
src/stepaudio2/utils.py
src/stepaudio2/cosyvoice2/__init__.py
src/stepaudio2/cosyvoice2/flow/__init__.py
src/stepaudio2/cosyvoice2/flow/decoder_dit.py
src/stepaudio2/cosyvoice2/flow/flow.py
src/stepaudio2/cosyvoice2/flow/flow_matching.py
src/stepaudio2/cosyvoice2/transformer/__init__.py
src/stepaudio2/cosyvoice2/transformer/attention.py
src/stepaudio2/cosyvoice2/transformer/embedding.py
src/stepaudio2/cosyvoice2/transformer/encoder_layer.py
src/stepaudio2/cosyvoice2/transformer/positionwise_feed_forward.py
src/stepaudio2/cosyvoice2/transformer/subsampling.py
src/stepaudio2/cosyvoice2/transformer/upsample_encoder_v2.py
src/stepaudio2/cosyvoice2/utils/__init__.py
src/stepaudio2/cosyvoice2/utils/class_utils.py
src/stepaudio2/cosyvoice2/utils/common.py
src/stepaudio2/cosyvoice2/utils/mask.py
src/stepaudio2/flashcosyvoice/__init__.py
src/stepaudio2/flashcosyvoice/cli.py
src/stepaudio2/flashcosyvoice/config.py
src/stepaudio2/flashcosyvoice/cosyvoice2.py
src/stepaudio2/flashcosyvoice/cosyvoice3.py
src/stepaudio2/flashcosyvoice/engine/__init__.py
src/stepaudio2/flashcosyvoice/engine/block_manager.py
src/stepaudio2/flashcosyvoice/engine/llm_engine.py
src/stepaudio2/flashcosyvoice/engine/model_runner.py
src/stepaudio2/flashcosyvoice/engine/scheduler.py
src/stepaudio2/flashcosyvoice/engine/sequence.py
src/stepaudio2/flashcosyvoice/modules/__init__.py
src/stepaudio2/flashcosyvoice/modules/flow.py
src/stepaudio2/flashcosyvoice/modules/hifigan.py
src/stepaudio2/flashcosyvoice/modules/qwen2.py
src/stepaudio2/flashcosyvoice/modules/sampler.py
src/stepaudio2/flashcosyvoice/modules/flow_components/__init__.py
src/stepaudio2/flashcosyvoice/modules/flow_components/estimator.py
src/stepaudio2/flashcosyvoice/modules/flow_components/upsample_encoder.py
src/stepaudio2/flashcosyvoice/modules/hifigan_components/__init__.py
src/stepaudio2/flashcosyvoice/modules/hifigan_components/layers.py
src/stepaudio2/flashcosyvoice/modules/qwen2_components/__init__.py
src/stepaudio2/flashcosyvoice/modules/qwen2_components/layers.py
src/stepaudio2/flashcosyvoice/utils/__init__.py
src/stepaudio2/flashcosyvoice/utils/audio.py
src/stepaudio2/flashcosyvoice/utils/context.py
src/stepaudio2/flashcosyvoice/utils/loader.py
src/stepaudio2/flashcosyvoice/utils/memory.py