SOURCES.txt

.gitignore
.gitmodules
LICENSE
README.md
requirements_ds_gpu.txt
setup.py
web_demo.py
web_demo_stream.py
Kimi-Audio-Evalkit/run_vita_audio.sh
Kimi-Audio-Evalkit/almeval/models/vita_audio.py
asset/2631296891109983590.wav
asset/379838640-d5ff0815-74f8-4738-b0f1-477cfc8dcc2d.wav
asset/4202818730519913143.wav
asset/logo.png
asset/piano.mp3
asset/qa_speed.gif
asset/tts_speed.gif
asset/vita-audio_logo.jpg
asset/wechat-group.jpg
asset/介绍一下上海.wav
asset/他本是我莲花池里养大的金鱼.wav
asset/发表一个悲伤的演讲.wav
asset/发表一个振奋人心的演讲.wav
configs/sts_finetune_stage1.yaml
configs/sts_finetune_stage2.yaml
evaluation/compute-acc-of-contain.py
evaluation/compute-cer.py
evaluation/compute-wer.py
evaluation/evaluate_asr.py
evaluation/evaluate_libritts.py
evaluation/evaluate_seedtts.py
evaluation/evaluate_sqa.py
evaluation/get_chat_template.py
scripts/set_env_ds_gpu.sh
scripts/deepspeed/ds_config_zero1.json
scripts/deepspeed/ds_config_zero2.json
scripts/deepspeed/ds_config_zero2_no_optimizer.json
scripts/deepspeed/ds_config_zero2_offload.json
scripts/deepspeed/ds_config_zero3.json
scripts/deepspeed/ds_config_zero3_offload.json
scripts/deepspeed/evaluate_sts.sh
scripts/deepspeed/sts_qwen25/finetune_glm4voice_mtp10_stage1.sh
scripts/deepspeed/sts_qwen25/finetune_glm4voice_mtp10_stage2.sh
scripts/deepspeed/sts_qwen25/finetune_glm4voice_mtp1_stage1.sh
scripts/deepspeed/sts_qwen25/finetune_glm4voice_stage1.sh
scripts/deepspeed/sts_qwen25/finetune_sensevoice_glm4voice_mtp10_stage1.sh
scripts/deepspeed/sts_qwen25/finetune_sensevoice_glm4voice_mtp10_stage2.sh
scripts/deepspeed/sts_qwen25/finetune_sensevoice_glm4voice_mtp1_stage1.sh
scripts/deepspeed/sts_qwen25/finetune_sensevoice_glm4voice_stage1.sh
tools/finetune_sts_v4_48_3.py
tools/get_neural_audio_codecs.py
tools/inference_sts.py
tools/trainer_v4_48_3.py
vita_audio/__init__.py
vita_audio/constants.py
vita_audio/tokenizer.py
vita_audio/tokenizer_cosyvoice2.py
vita_audio/tokenizer_glm4voice.py
vita_audio/tokenizer_sensevoice_glm4voice.py
vita_audio/tokenizer_sensevoice_sparktts.py
vita_audio/tokenizer_snac.py
vita_audio.egg-info/PKG-INFO
vita_audio.egg-info/SOURCES.txt
vita_audio.egg-info/dependency_links.txt
vita_audio.egg-info/top_level.txt
vita_audio/data/__init__.py
vita_audio/data/build.py
vita_audio/data/data_collator.py
vita_audio/data/dataset_base.py
vita_audio/data/dataset_cosyvoice2.py
vita_audio/data/dataset_deepseek.py
vita_audio/data/dataset_hunyuan.py
vita_audio/data/dataset_llama3.py
vita_audio/data/dataset_mistral.py
vita_audio/data/dataset_qwen2.py
vita_audio/data/utils.py
vita_audio/data/processor/__init__.py
vita_audio/data/processor/audio_processor.py
vita_audio/data/processor/image_processor.py
vita_audio/models/__init__.py
vita_audio/models/qwen2_mtp_sensevoice_v4_48_3/__init__.py
vita_audio/models/qwen2_mtp_sensevoice_v4_48_3/config_7B_mtp0.json
vita_audio/models/qwen2_mtp_sensevoice_v4_48_3/config_7B_mtp1.json
vita_audio/models/qwen2_mtp_sensevoice_v4_48_3/config_7B_mtp10.json
vita_audio/models/qwen2_mtp_sensevoice_v4_48_3/configuration_qwen2.py
vita_audio/models/qwen2_mtp_sensevoice_v4_48_3/modeling_qwen2.py
vita_audio/models/qwen2_mtp_sensevoice_v4_48_3/modeling_sensevoice.py
vita_audio/models/qwen2_mtp_sensevoice_v4_48_3/modular_qwen2.py
vita_audio/models/qwen2_mtp_sensevoice_v4_48_3/resampler_projector.py
vita_audio/models/qwen2_mtp_sensevoice_v4_48_3/tokenization_qwen2.py
vita_audio/models/qwen2_mtp_sensevoice_v4_48_3/tokenization_qwen2_fast.py
vita_audio/models/qwen2_mtp_sensevoice_v4_48_3/tokenizer_config.json
vita_audio/models/qwen2_mtp_v4_48_3/__init__.py
vita_audio/models/qwen2_mtp_v4_48_3/config_7B_mtp1.json
vita_audio/models/qwen2_mtp_v4_48_3/config_7B_mtp10.json
vita_audio/models/qwen2_mtp_v4_48_3/configuration_qwen2.py
vita_audio/models/qwen2_mtp_v4_48_3/generation_config.json
vita_audio/models/qwen2_mtp_v4_48_3/modeling_qwen2.py
vita_audio/models/qwen2_mtp_v4_48_3/modular_qwen2.py
vita_audio/models/qwen2_mtp_v4_48_3/tokenization_qwen2.py
vita_audio/models/qwen2_mtp_v4_48_3/tokenization_qwen2_fast.py
vita_audio/models/qwen2_mtp_v4_48_3/tokenizer_config.json
vita_audio/models/qwen2_v4_48_3/__init__.py
vita_audio/models/qwen2_v4_48_3/configuration_qwen2.py
vita_audio/models/qwen2_v4_48_3/modeling_qwen2.py
vita_audio/models/qwen2_v4_48_3/modular_qwen2.py
vita_audio/models/qwen2_v4_48_3/tokenization_qwen2.py
vita_audio/models/qwen2_v4_48_3/tokenization_qwen2_fast.py
web/parms.py
web/pem.py
web/pool.py
web/queue.py
web/requirements.txt
web/vad.py
web/resources/index.html
web/resources/silero_vad.jit
web/resources/silero_vad.onnx