返回模型
暂无说明文档
AXERA-TECH/CosyVoice2
作者 AXERA-TECH
text-to-speech
transformers
↓ 12
♥ 2
创建时间: 2025-09-04 12:32:39+00:00
更新时间: 2025-09-30 12:21:23+00:00
在 Hugging Face 上查看文件 (131)
.gitattributes
.gitignore
CosyVoice-BlankEN-Ax650-prefill_512/llm.llm_embedding.float16.bin
CosyVoice-BlankEN-Ax650-prefill_512/llm.llm_embedding.float32.bin
CosyVoice-BlankEN-Ax650-prefill_512/llm.llm_embedding.npy
CosyVoice-BlankEN-Ax650-prefill_512/llm.speech_embedding.float16.bin
CosyVoice-BlankEN-Ax650-prefill_512/llm.speech_embedding.float32.bin
CosyVoice-BlankEN-Ax650-prefill_512/llm.speech_embedding.npy
CosyVoice-BlankEN-Ax650-prefill_512/llm_decoder.axmodel
CosyVoice-BlankEN-Ax650-prefill_512/model.embed_tokens.weight.bfloat16.bin
CosyVoice-BlankEN-Ax650-prefill_512/model.embed_tokens.weight.float32.bin
CosyVoice-BlankEN-Ax650-prefill_512/model.embed_tokens.weight.npy
CosyVoice-BlankEN-Ax650-prefill_512/qwen2_p128_l0_together.axmodel
CosyVoice-BlankEN-Ax650-prefill_512/qwen2_p128_l10_together.axmodel
CosyVoice-BlankEN-Ax650-prefill_512/qwen2_p128_l11_together.axmodel
CosyVoice-BlankEN-Ax650-prefill_512/qwen2_p128_l12_together.axmodel
CosyVoice-BlankEN-Ax650-prefill_512/qwen2_p128_l13_together.axmodel
CosyVoice-BlankEN-Ax650-prefill_512/qwen2_p128_l14_together.axmodel
CosyVoice-BlankEN-Ax650-prefill_512/qwen2_p128_l15_together.axmodel
CosyVoice-BlankEN-Ax650-prefill_512/qwen2_p128_l16_together.axmodel
CosyVoice-BlankEN-Ax650-prefill_512/qwen2_p128_l17_together.axmodel
CosyVoice-BlankEN-Ax650-prefill_512/qwen2_p128_l18_together.axmodel
CosyVoice-BlankEN-Ax650-prefill_512/qwen2_p128_l19_together.axmodel
CosyVoice-BlankEN-Ax650-prefill_512/qwen2_p128_l1_together.axmodel
CosyVoice-BlankEN-Ax650-prefill_512/qwen2_p128_l20_together.axmodel
CosyVoice-BlankEN-Ax650-prefill_512/qwen2_p128_l21_together.axmodel
CosyVoice-BlankEN-Ax650-prefill_512/qwen2_p128_l22_together.axmodel
CosyVoice-BlankEN-Ax650-prefill_512/qwen2_p128_l23_together.axmodel
CosyVoice-BlankEN-Ax650-prefill_512/qwen2_p128_l2_together.axmodel
CosyVoice-BlankEN-Ax650-prefill_512/qwen2_p128_l3_together.axmodel
CosyVoice-BlankEN-Ax650-prefill_512/qwen2_p128_l4_together.axmodel
CosyVoice-BlankEN-Ax650-prefill_512/qwen2_p128_l5_together.axmodel
CosyVoice-BlankEN-Ax650-prefill_512/qwen2_p128_l6_together.axmodel
CosyVoice-BlankEN-Ax650-prefill_512/qwen2_p128_l7_together.axmodel
CosyVoice-BlankEN-Ax650-prefill_512/qwen2_p128_l8_together.axmodel
CosyVoice-BlankEN-Ax650-prefill_512/qwen2_p128_l9_together.axmodel
CosyVoice-BlankEN-Ax650-prefill_512/qwen2_post.axmodel
README.md
asset/en_man1.mp3
asset/en_man1.txt
asset/en_woman1.mp3
asset/en_woman1.txt
asset/output.wav
asset/zh_man1.txt
asset/zh_man1.wav
asset/zh_man2.mp3
asset/zh_man2.txt
asset/zh_woman1.txt
asset/zh_woman1.wav
config.json
frontend-onnx/campplus.onnx
ONNX
frontend-onnx/speech_tokenizer_v2.onnx
ONNX
gradio.png
main_api_ax650
main_api_axcl_aarch64
main_api_axcl_x86
main_ax650
main_axcl_aarch64
main_axcl_x86
onnxruntime-linux-aarch64-1.23.0/GIT_COMMIT_ID
onnxruntime-linux-aarch64-1.23.0/LICENSE
onnxruntime-linux-aarch64-1.23.0/Privacy.md
onnxruntime-linux-aarch64-1.23.0/README.md
onnxruntime-linux-aarch64-1.23.0/ThirdPartyNotices.txt
onnxruntime-linux-aarch64-1.23.0/VERSION_NUMBER
onnxruntime-linux-aarch64-1.23.0/lib/cmake/onnxruntime/onnxruntimeConfig.cmake
onnxruntime-linux-aarch64-1.23.0/lib/cmake/onnxruntime/onnxruntimeConfigVersion.cmake
onnxruntime-linux-aarch64-1.23.0/lib/cmake/onnxruntime/onnxruntimeTargets-release.cmake
onnxruntime-linux-aarch64-1.23.0/lib/cmake/onnxruntime/onnxruntimeTargets.cmake
onnxruntime-linux-aarch64-1.23.0/lib/libonnxruntime.so
onnxruntime-linux-aarch64-1.23.0/lib/libonnxruntime.so.1
onnxruntime-linux-aarch64-1.23.0/lib/libonnxruntime.so.1.23.0
onnxruntime-linux-aarch64-1.23.0/lib/libonnxruntime_providers_shared.so
onnxruntime-linux-aarch64-1.23.0/lib/pkgconfig/libonnxruntime.pc
onnxruntime-linux-x64-1.23.0/GIT_COMMIT_ID
onnxruntime-linux-x64-1.23.0/LICENSE
onnxruntime-linux-x64-1.23.0/Privacy.md
onnxruntime-linux-x64-1.23.0/README.md
onnxruntime-linux-x64-1.23.0/ThirdPartyNotices.txt
onnxruntime-linux-x64-1.23.0/VERSION_NUMBER
onnxruntime-linux-x64-1.23.0/lib/cmake/onnxruntime/onnxruntimeConfig.cmake
onnxruntime-linux-x64-1.23.0/lib/cmake/onnxruntime/onnxruntimeConfigVersion.cmake
onnxruntime-linux-x64-1.23.0/lib/cmake/onnxruntime/onnxruntimeTargets-release.cmake
onnxruntime-linux-x64-1.23.0/lib/cmake/onnxruntime/onnxruntimeTargets.cmake
onnxruntime-linux-x64-1.23.0/lib/libonnxruntime.so
onnxruntime-linux-x64-1.23.0/lib/libonnxruntime.so.1
onnxruntime-linux-x64-1.23.0/lib/libonnxruntime.so.1.23.0
onnxruntime-linux-x64-1.23.0/lib/libonnxruntime_providers_shared.so
onnxruntime-linux-x64-1.23.0/lib/pkgconfig/libonnxruntime.pc
prompt_files/flow_embedding.txt
prompt_files/flow_prompt_speech_token.txt
prompt_files/llm_embedding.txt
prompt_files/llm_prompt_speech_token.txt
prompt_files/prompt_speech_feat.txt
prompt_files/prompt_text.txt
run_api_ax650.sh
run_api_axcl_aarch64.sh
run_api_axcl_x86.sh
run_ax650.sh
run_axcl_aarch64.sh
run_axcl_x86.sh
scripts/CosyVoice-BlankEN/merges.txt
scripts/CosyVoice-BlankEN/tokenizer_config.json
scripts/CosyVoice-BlankEN/vocab.json
scripts/audio.py
scripts/cosyvoice2_tokenizer.py
scripts/frontend.py
scripts/gradio_demo.py
scripts/meldataset.py
scripts/process_prompt.py
scripts/requirements.txt
scripts/tokenizer/assets/multilingual_zh_ja_yue_char_del.tiktoken
scripts/tokenizer/tokenizer.py
token2wav-axmodels/flow.input_embedding.float16.bin
token2wav-axmodels/flow.input_embedding.float32.bin
token2wav-axmodels/flow.input_embedding.npy
token2wav-axmodels/flow_encoder_28.axmodel
token2wav-axmodels/flow_encoder_50_final.axmodel
token2wav-axmodels/flow_encoder_53.axmodel
token2wav-axmodels/flow_encoder_78.axmodel
token2wav-axmodels/flow_estimator_200.axmodel
token2wav-axmodels/flow_estimator_250.axmodel
token2wav-axmodels/flow_estimator_300.axmodel
token2wav-axmodels/hift_p1_50_first.mnn
token2wav-axmodels/hift_p1_50_first.onnx
ONNX
token2wav-axmodels/hift_p1_58.mnn
token2wav-axmodels/hift_p1_58.onnx
ONNX
token2wav-axmodels/hift_p2_50_first.axmodel
token2wav-axmodels/hift_p2_58.axmodel
token2wav-axmodels/rand_noise_1_80_300.txt
token2wav-axmodels/speech_window_2x8x480.txt