search

modelscope / FunCodec

FunCodec is a research-oriented toolkit for audio quantization and downstream applications, such as text-to-speech synthesis, music generation et.al.
https://funcodec.github.io/
MIT License
370 stars 30 forks source link

Getting error while testing LauraTTS #6

Closed rishikksh20 closed 11 months ago

rishikksh20 commented 11 months ago

Hi @ZhihaoDU while running LauraTTS from egs/LibriTTS/text2speech_laura README I am getting error which described below.

When using ModelScope, getting following error:

Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File "/home/rishikesh/.local/lib/python3.10/site-packages/modelscope/pipelines/builder.py", line 170, in pipeline
    return build_pipeline(cfg, task_name=task)
  File "/home/rishikesh/.local/lib/python3.10/site-packages/modelscope/pipelines/builder.py", line 65, in build_pipeline
    return build_from_cfg(
  File "/home/rishikesh/.local/lib/python3.10/site-packages/modelscope/utils/registry.py", line 198, in build_from_cfg
    raise KeyError(
KeyError: 'laura-codec-tts-inference is not in the pipelines registry group text-to-speech. Please make sure the correct version of ModelScope library is used.'

While running bash command, getting following error:

File "/usr/lib/python3.10/runpy.py", line 196, in _run_module_as_main
    return _run_code(code, main_globals, None,
  File "/usr/lib/python3.10/runpy.py", line 86, in _run_code
    exec(code, run_globals)
  File "/home/rishikesh/code/FunCodec/funcodec/bin/text2audio_inference.py", line 561, in <module>
    main()
  File "/home/rishikesh/code/FunCodec/funcodec/bin/text2audio_inference.py", line 557, in main
    inference(**kwargs)
  File "/home/rishikesh/code/FunCodec/funcodec/bin/text2audio_inference.py", line 381, in inference
    inference_pipeline = inference_func(
  File "/home/rishikesh/code/FunCodec/funcodec/bin/text2audio_inference.py", line 287, in inference_func
    my_model = Text2Audio.from_pretrained(
  File "/home/rishikesh/code/FunCodec/funcodec/bin/text2audio_inference.py", line 227, in from_pretrained
    return Text2Audio(**kwargs)
  File "/home/rishikesh/code/FunCodec/funcodec/bin/text2audio_inference.py", line 53, in __init__
    model, model_args = Text2AudioGenTask.build_model_from_file(
  File "/home/rishikesh/code/FunCodec/funcodec/tasks/abs_task.py", line 1928, in build_model_from_file
    model = cls.build_model(args)
  File "/home/rishikesh/code/FunCodec/funcodec/tasks/text2audio_generation.py", line 206, in build_model
    if args.text_encoder is not None:
AttributeError: 'Namespace' object has no attribute 'text_encoder'

FYI : Bash issue is ressolved

ZhihaoDU commented 11 months ago

Thanks for your error reporting. ModelScope approach requires the latest version of ModelScope lib, which is at the internal test stage currently. I believe this version will release at the end of December, you can try ModelScope approach again in Jan. 2024. I sorry to say, currently, only bash approach is supported.