FunAudioLLM / CosyVoice

Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.
https://funaudiollm.github.io/
Apache License 2.0
4.84k stars 492 forks source link

这是什么意思 #273

Open plasticlove738 opened 1 month ago

plasticlove738 commented 1 month ago

(cosyvoice) root@amax:/data/xyw23131036/cosyvoice/CosyVoice# PYTHONPATH=third_party/Matcha-TTS python api.py 2024-08-11 14:11:31,215 - modelscope - INFO - PyTorch version 2.0.1+cu118 Found. 2024-08-11 14:11:31,216 - modelscope - INFO - Loading ast index from /root/.cache/modelscope/ast_indexer 2024-08-11 14:11:31,245 - modelscope - INFO - Loading done! Current index file version is 1.15.0, with md5 4b288142160eff9dde432695529dc918 and a total number of 980 components indexed failed to import ttsfrd, use WeTextProcessing instead /opt/anaconda3/envs/cosyvoice/lib/python3.8/site-packages/torch/_jit_internal.py:726: FutureWarning: ignore(True) has been deprecated. TorchScript will now drop the function call on compilation. Use torch.jit.unused now. {} warnings.warn( /opt/anaconda3/envs/cosyvoice/lib/python3.8/site-packages/diffusers/models/lora.py:393: FutureWarning: LoRACompatibleLinear is deprecated and will be removed in version 1.0.0. Use of LoRACompatibleLinear is deprecated. Please switch to PEFT backend by installing PEFT: pip install peft. deprecate("LoRACompatibleLinear", "1.0.0", deprecation_message) 2024-08-11 14:11:39.692424345 [W:onnxruntime:, session_state.cc:1162 VerifyEachNodeIsAssignedToAnEp] Some nodes were not assigned to the preferred execution providers which may or may not have an negative impact on performance. e.g. ORT explicitly assigns shape related ops to CPU to improve perf. 2024-08-11 14:11:39.692451160 [W:onnxruntime:, session_state.cc:1164 VerifyEachNodeIsAssignedToAnEp] Rerunning with verbose output on a non-minimal build will show node assignments. 2024-08-11 14:11:39,872 WETEXT INFO found existing fst: /opt/anaconda3/envs/cosyvoice/lib/python3.8/site-packages/tn/zh_tn_tagger.fst INFO:wetext-zh_normalizer:found existing fst: /opt/anaconda3/envs/cosyvoice/lib/python3.8/site-packages/tn/zh_tn_tagger.fst 2024-08-11 14:11:39,872 WETEXT INFO /opt/anaconda3/envs/cosyvoice/lib/python3.8/site-packages/tn/zh_tn_verbalizer.fst INFO:wetext-zh_normalizer: /opt/anaconda3/envs/cosyvoice/lib/python3.8/site-packages/tn/zh_tn_verbalizer.fst 2024-08-11 14:11:39,872 WETEXT INFO skip building fst for zh_normalizer ... INFO:wetext-zh_normalizer:skip building fst for zh_normalizer ... 2024-08-11 14:11:40,199 WETEXT INFO found existing fst: /opt/anaconda3/envs/cosyvoice/lib/python3.8/site-packages/tn/en_tn_tagger.fst INFO:wetext-en_normalizer:found existing fst: /opt/anaconda3/envs/cosyvoice/lib/python3.8/site-packages/tn/en_tn_tagger.fst 2024-08-11 14:11:40,199 WETEXT INFO /opt/anaconda3/envs/cosyvoice/lib/python3.8/site-packages/tn/en_tn_verbalizer.fst INFO:wetext-en_normalizer: /opt/anaconda3/envs/cosyvoice/lib/python3.8/site-packages/tn/en_tn_verbalizer.fst 2024-08-11 14:11:40,199 WETEXT INFO skip building fst for en_normalizer ... INFO:wetext-en_normalizer:skip building fst for en_normalizer ... ['中文女', '中文男', '日语男', '粤语女', '英文女', '英文男', '韩语女'] Traceback (most recent call last): File "api.py", line 25, in uvicorn.run(app, NameError: name 'uvicorn' is not defined

aluminumbox commented 1 month ago

fastapi.py is supported by community developers, you can ask such question in our dingding group

github-actions[bot] commented 1 week ago

This issue is stale because it has been open for 30 days with no activity.