Delete files asr_0.wav assets/svqa_0.jpg assets/vqa_0.png chat_template.txt magvit_tokenizer/__init__.py magvit_tokenizer/common_modules.py magvit_tokenizer/misc.py magvit_tokenizer/modeling_magvitv2.py magvit_tokenizer/modeling_utils.py omni_diffusion/__init__.py omni_diffusion/constants.py omni_diffusion/data/__init__.py omni_diffusion/data/build.py omni_diffusion/data/data_collator.py omni_diffusion/data/dataset_base.py omni_diffusion/data/dataset_qwen2.py omni_diffusion/data/processor/__init__.py omni_diffusion/data/processor/audio_processor.py omni_diffusion/data/processor/image_processor.py omni_diffusion/data/utils.py omni_diffusion/models/__init__.py omni_diffusion/models/dream/__init__.py omni_diffusion/models/dream/config.yaml omni_diffusion/models/dream/config_dream_resume.json omni_diffusion/models/dream/configuration.json omni_diffusion/models/dream/configuration_dream.py omni_diffusion/models/dream/generation_utils.py omni_diffusion/models/dream/modeling_dream.py omni_diffusion/models/dream/modeling_sensevoice.py omni_diffusion/models/dream/resampler_projector.py omni_diffusion/models/dream/tokenization_dream.py omni_diffusion/models/dream/tokenizer_config.json omni_diffusion/models/magvit/common_modules.py omni_diffusion/models/magvit/misc.py omni_diffusion/models/magvit/modeling_magvitv2.py omni_diffusion/models/magvit/modeling_utils.py omni_diffusion/tokenizer.py omni_diffusion/tokenizer_magvitv2.py omni_diffusion/tokenizer_sensevoice_glm4voice.py s2i_0.wav svqa_0.jpg svqa_0.wav third_party/GLM-4-Voice/.gitignore third_party/GLM-4-Voice/LICENSE third_party/GLM-4-Voice/README.md third_party/GLM-4-Voice/README_en.md third_party/GLM-4-Voice/audio_process.py third_party/GLM-4-Voice/cosyvoice/__init__.py third_party/GLM-4-Voice/cosyvoice/bin/inference.py third_party/GLM-4-Voice/cosyvoice/bin/train.py third_party/GLM-4-Voice/cosyvoice/cli/__init__.py third_party/GLM-4-Voice/cosyvoice/cli/cosyvoice.py third_party/GLM-4-Voice/cosyvoice/cli/frontend.py third_party/GLM-4-Voice/cosyvoice/cli/model.py third_party/GLM-4-Voice/cosyvoice/dataset/__init__.py third_party/GLM-4-Voice/cosyvoice/dataset/dataset.py third_party/GLM-4-Voice/cosyvoice/dataset/processor.py third_party/GLM-4-Voice/cosyvoice/flow/decoder.py third_party/GLM-4-Voice/cosyvoice/flow/flow.py third_party/GLM-4-Voice/cosyvoice/flow/flow_gradtts.py third_party/GLM-4-Voice/cosyvoice/flow/flow_matching.py third_party/GLM-4-Voice/cosyvoice/flow/flow_matching_dit.py third_party/GLM-4-Voice/cosyvoice/flow/length_regulator.py third_party/GLM-4-Voice/cosyvoice/flow/stable/adp.py third_party/GLM-4-Voice/cosyvoice/flow/stable/blocks.py third_party/GLM-4-Voice/cosyvoice/flow/stable/dit.py third_party/GLM-4-Voice/cosyvoice/flow/stable/dit_v2.py third_party/GLM-4-Voice/cosyvoice/flow/stable/sampling.py third_party/GLM-4-Voice/cosyvoice/flow/stable/stable_diffusion.py third_party/GLM-4-Voice/cosyvoice/flow/stable/stable_diffusion_test.py third_party/GLM-4-Voice/cosyvoice/flow/stable/transformer.py third_party/GLM-4-Voice/cosyvoice/flow/stable/transformer_use_mask.py third_party/GLM-4-Voice/cosyvoice/hifigan/f0_predictor.py third_party/GLM-4-Voice/cosyvoice/hifigan/generator.py third_party/GLM-4-Voice/cosyvoice/llm/llm.py third_party/GLM-4-Voice/cosyvoice/transformer/__init__.py third_party/GLM-4-Voice/cosyvoice/transformer/activation.py third_party/GLM-4-Voice/cosyvoice/transformer/attention.py third_party/GLM-4-Voice/cosyvoice/transformer/convolution.py third_party/GLM-4-Voice/cosyvoice/transformer/decoder.py third_party/GLM-4-Voice/cosyvoice/transformer/decoder_layer.py third_party/GLM-4-Voice/cosyvoice/transformer/embedding.py third_party/GLM-4-Voice/cosyvoice/transformer/encoder.py third_party/GLM-4-Voice/cosyvoice/transformer/encoder_layer.py third_party/GLM-4-Voice/cosyvoice/transformer/label_smoothing_loss.py third_party/GLM-4-Voice/cosyvoice/transformer/positionwise_feed_forward.py third_party/GLM-4-Voice/cosyvoice/transformer/subsampling.py third_party/GLM-4-Voice/cosyvoice/utils/__init__.py third_party/GLM-4-Voice/cosyvoice/utils/block_mask_util.py third_party/GLM-4-Voice/cosyvoice/utils/class_utils.py third_party/GLM-4-Voice/cosyvoice/utils/common.py third_party/GLM-4-Voice/cosyvoice/utils/executor.py third_party/GLM-4-Voice/cosyvoice/utils/file_utils.py third_party/GLM-4-Voice/cosyvoice/utils/frontend_utils.py third_party/GLM-4-Voice/cosyvoice/utils/mask.py third_party/GLM-4-Voice/cosyvoice/utils/scheduler.py third_party/GLM-4-Voice/cosyvoice/utils/train_utils.py third_party/GLM-4-Voice/flow_inference.py third_party/GLM-4-Voice/model_server.py third_party/GLM-4-Voice/requirements.txt third_party/GLM-4-Voice/resources/architecture.jpeg third_party/GLM-4-Voice/resources/web_demo.png third_party/GLM-4-Voice/speech_tokenizer/__init__.py third_party/GLM-4-Voice/speech_tokenizer/configuration_whisper.py third_party/GLM-4-Voice/speech_tokenizer/generation_whisper.py third_party/GLM-4-Voice/speech_tokenizer/modeling_whisper.py third_party/GLM-4-Voice/speech_tokenizer/utils.py third_party/GLM-4-Voice/third_party/Matcha-TTS/.env.example third_party/GLM-4-Voice/third_party/Matcha-TTS/.github/PULL_REQUEST_TEMPLATE.md third_party/GLM-4-Voice/third_party/Matcha-TTS/.github/codecov.yml third_party/GLM-4-Voice/third_party/Matcha-TTS/.github/dependabot.yml third_party/GLM-4-Voice/third_party/Matcha-TTS/.github/release-drafter.yml third_party/GLM-4-Voice/third_party/Matcha-TTS/.gitignore third_party/GLM-4-Voice/third_party/Matcha-TTS/.pre-commit-config.yaml third_party/GLM-4-Voice/third_party/Matcha-TTS/.project-root third_party/GLM-4-Voice/third_party/Matcha-TTS/.pylintrc third_party/GLM-4-Voice/third_party/Matcha-TTS/LICENSE third_party/GLM-4-Voice/third_party/Matcha-TTS/MANIFEST.in third_party/GLM-4-Voice/third_party/Matcha-TTS/Makefile third_party/GLM-4-Voice/third_party/Matcha-TTS/README.md third_party/GLM-4-Voice/third_party/Matcha-TTS/configs/__init__.py third_party/GLM-4-Voice/third_party/Matcha-TTS/configs/callbacks/default.yaml third_party/GLM-4-Voice/third_party/Matcha-TTS/configs/callbacks/model_checkpoint.yaml third_party/GLM-4-Voice/third_party/Matcha-TTS/configs/callbacks/model_summary.yaml third_party/GLM-4-Voice/third_party/Matcha-TTS/configs/callbacks/none.yaml third_party/GLM-4-Voice/third_party/Matcha-TTS/configs/callbacks/rich_progress_bar.yaml third_party/GLM-4-Voice/third_party/Matcha-TTS/configs/data/hi-fi_en-US_female.yaml third_party/GLM-4-Voice/third_party/Matcha-TTS/configs/data/ljspeech.yaml third_party/GLM-4-Voice/third_party/Matcha-TTS/configs/data/vctk.yaml third_party/GLM-4-Voice/third_party/Matcha-TTS/configs/debug/default.yaml third_party/GLM-4-Voice/third_party/Matcha-TTS/configs/debug/fdr.yaml third_party/GLM-4-Voice/third_party/Matcha-TTS/configs/debug/limit.yaml third_party/GLM-4-Voice/third_party/Matcha-TTS/configs/debug/overfit.yaml third_party/GLM-4-Voice/third_party/Matcha-TTS/configs/debug/profiler.yaml third_party/GLM-4-Voice/third_party/Matcha-TTS/configs/eval.yaml third_party/GLM-4-Voice/third_party/Matcha-TTS/configs/experiment/hifi_dataset_piper_phonemizer.yaml third_party/GLM-4-Voice/third_party/Matcha-TTS/configs/experiment/ljspeech.yaml third_party/GLM-4-Voice/third_party/Matcha-TTS/configs/experiment/ljspeech_from_durations.yaml third_party/GLM-4-Voice/third_party/Matcha-TTS/configs/experiment/ljspeech_min_memory.yaml third_party/GLM-4-Voice/third_party/Matcha-TTS/configs/experiment/multispeaker.yaml third_party/GLM-4-Voice/third_party/Matcha-TTS/configs/extras/default.yaml third_party/GLM-4-Voice/third_party/Matcha-TTS/configs/hparams_search/mnist_optuna.yaml third_party/GLM-4-Voice/third_party/Matcha-TTS/configs/hydra/default.yaml third_party/GLM-4-Voice/third_party/Matcha-TTS/configs/local/.gitkeep third_party/GLM-4-Voice/third_party/Matcha-TTS/configs/logger/aim.yaml third_party/GLM-4-Voice/third_party/Matcha-TTS/configs/logger/comet.yaml third_party/GLM-4-Voice/third_party/Matcha-TTS/configs/logger/csv.yaml third_party/GLM-4-Voice/third_party/Matcha-TTS/configs/logger/many_loggers.yaml third_party/GLM-4-Voice/third_party/Matcha-TTS/configs/logger/mlflow.yaml third_party/GLM-4-Voice/third_party/Matcha-TTS/configs/logger/neptune.yaml third_party/GLM-4-Voice/third_party/Matcha-TTS/configs/logger/tensorboard.yaml third_party/GLM-4-Voice/third_party/Matcha-TTS/configs/logger/wandb.yaml third_party/GLM-4-Voice/third_party/Matcha-TTS/configs/model/cfm/default.yaml third_party/GLM-4-Voice/third_party/Matcha-TTS/configs/model/decoder/default.yaml third_party/GLM-4-Voice/third_party/Matcha-TTS/configs/model/encoder/default.yaml third_party/GLM-4-Voice/third_party/Matcha-TTS/configs/model/matcha.yaml third_party/GLM-4-Voice/third_party/Matcha-TTS/configs/model/optimizer/adam.yaml third_party/GLM-4-Voice/third_party/Matcha-TTS/configs/paths/default.yaml third_party/GLM-4-Voice/third_party/Matcha-TTS/configs/train.yaml third_party/GLM-4-Voice/third_party/Matcha-TTS/configs/trainer/cpu.yaml third_party/GLM-4-Voice/third_party/Matcha-TTS/configs/trainer/ddp.yaml third_party/GLM-4-Voice/third_party/Matcha-TTS/configs/trainer/ddp_sim.yaml third_party/GLM-4-Voice/third_party/Matcha-TTS/configs/trainer/default.yaml third_party/GLM-4-Voice/third_party/Matcha-TTS/configs/trainer/gpu.yaml third_party/GLM-4-Voice/third_party/Matcha-TTS/configs/trainer/mps.yaml third_party/GLM-4-Voice/third_party/Matcha-TTS/matcha/VERSION third_party/GLM-4-Voice/third_party/Matcha-TTS/matcha/__init__.py third_party/GLM-4-Voice/third_party/Matcha-TTS/matcha/app.py third_party/GLM-4-Voice/third_party/Matcha-TTS/matcha/cli.py third_party/GLM-4-Voice/third_party/Matcha-TTS/matcha/data/__init__.py third_party/GLM-4-Voice/third_party/Matcha-TTS/matcha/data/components/__init__.py third_party/GLM-4-Voice/third_party/Matcha-TTS/matcha/data/text_mel_datamodule.py third_party/GLM-4-Voice/third_party/Matcha-TTS/matcha/hifigan/LICENSE third_party/GLM-4-Voice/third_party/Matcha-TTS/matcha/hifigan/README.md third_party/GLM-4-Voice/third_party/Matcha-TTS/matcha/hifigan/__init__.py third_party/GLM-4-Voice/third_party/Matcha-TTS/matcha/hifigan/config.py third_party/GLM-4-Voice/third_party/Matcha-TTS/matcha/hifigan/denoiser.py third_party/GLM-4-Voice/third_party/Matcha-TTS/matcha/hifigan/env.py third_party/GLM-4-Voice/third_party/Matcha-TTS/matcha/hifigan/meldataset.py third_party/GLM-4-Voice/third_party/Matcha-TTS/matcha/hifigan/models.py third_party/GLM-4-Voice/third_party/Matcha-TTS/matcha/hifigan/xutils.py third_party/GLM-4-Voice/third_party/Matcha-TTS/matcha/models/__init__.py third_party/GLM-4-Voice/third_party/Matcha-TTS/matcha/models/baselightningmodule.py third_party/GLM-4-Voice/third_party/Matcha-TTS/matcha/models/components/__init__.py third_party/GLM-4-Voice/third_party/Matcha-TTS/matcha/models/components/decoder.py third_party/GLM-4-Voice/third_party/Matcha-TTS/matcha/models/components/flow_matching.py third_party/GLM-4-Voice/third_party/Matcha-TTS/matcha/models/components/text_encoder.py third_party/GLM-4-Voice/third_party/Matcha-TTS/matcha/models/components/transformer.py third_party/GLM-4-Voice/third_party/Matcha-TTS/matcha/models/matcha_tts.py third_party/GLM-4-Voice/third_party/Matcha-TTS/matcha/onnx/__init__.py third_party/GLM-4-Voice/third_party/Matcha-TTS/matcha/onnx/export.py third_party/GLM-4-Voice/third_party/Matcha-TTS/matcha/onnx/infer.py third_party/GLM-4-Voice/third_party/Matcha-TTS/matcha/text/__init__.py third_party/GLM-4-Voice/third_party/Matcha-TTS/matcha/text/cleaners.py third_party/GLM-4-Voice/third_party/Matcha-TTS/matcha/text/numbers.py third_party/GLM-4-Voice/third_party/Matcha-TTS/matcha/text/symbols.py third_party/GLM-4-Voice/third_party/Matcha-TTS/matcha/train.py third_party/GLM-4-Voice/third_party/Matcha-TTS/matcha/utils/__init__.py third_party/GLM-4-Voice/third_party/Matcha-TTS/matcha/utils/audio.py third_party/GLM-4-Voice/third_party/Matcha-TTS/matcha/utils/data/__init__.py third_party/GLM-4-Voice/third_party/Matcha-TTS/matcha/utils/data/hificaptain.py third_party/GLM-4-Voice/third_party/Matcha-TTS/matcha/utils/data/ljspeech.py third_party/GLM-4-Voice/third_party/Matcha-TTS/matcha/utils/data/utils.py third_party/GLM-4-Voice/third_party/Matcha-TTS/matcha/utils/generate_data_statistics.py third_party/GLM-4-Voice/third_party/Matcha-TTS/matcha/utils/get_durations_from_trained_model.py third_party/GLM-4-Voice/third_party/Matcha-TTS/matcha/utils/instantiators.py third_party/GLM-4-Voice/third_party/Matcha-TTS/matcha/utils/logging_utils.py third_party/GLM-4-Voice/third_party/Matcha-TTS/matcha/utils/model.py third_party/GLM-4-Voice/third_party/Matcha-TTS/matcha/utils/monotonic_align/__init__.py third_party/GLM-4-Voice/third_party/Matcha-TTS/matcha/utils/monotonic_align/core.pyx third_party/GLM-4-Voice/third_party/Matcha-TTS/matcha/utils/monotonic_align/setup.py third_party/GLM-4-Voice/third_party/Matcha-TTS/matcha/utils/pylogger.py third_party/GLM-4-Voice/third_party/Matcha-TTS/matcha/utils/rich_utils.py third_party/GLM-4-Voice/third_party/Matcha-TTS/matcha/utils/utils.py third_party/GLM-4-Voice/third_party/Matcha-TTS/notebooks/.gitkeep third_party/GLM-4-Voice/third_party/Matcha-TTS/pyproject.toml third_party/GLM-4-Voice/third_party/Matcha-TTS/requirements.txt third_party/GLM-4-Voice/third_party/Matcha-TTS/scripts/schedule.sh third_party/GLM-4-Voice/third_party/Matcha-TTS/setup.py third_party/GLM-4-Voice/third_party/Matcha-TTS/synthesis.ipynb third_party/GLM-4-Voice/web_demo.py vqa_0.png with huggingface_hub
verified 
multimodalart HF Staff commited on 
