• <xmp id="om0om">
  • <table id="om0om"><noscript id="om0om"></noscript></table>
  • Conversational AI / NLP

    NVIDIA NeMo Canary ??? ?? ?? ? ??? ?? ??? ??

    Reading Time: 3 minutes

    NVIDIA NeMo? ????? ?????? ???? ???? ??? ???? ??? AI ??? ???? ?? ?? ? ?? ??????.

    ?? NeMo ?? ??, ????, ???, ????? ??? ??? ? ????? ?? ???? ??? ??Canary? ??????. Canary? ??? ?? 3?? ?? ?? ?? ??? ??? ?????.?

    ?? 1. ??, ???, ????, ????? ???? ???? Canary ??

    ? ?????? Canary ??? ?? ??? ?? ??? ?????.

    Canary ??

    Canary? HuggingFace Open ASR ????? ?? 6.67%? ?? ???(WER)? 1?? ??????. ?? ?? ?? ??? ?? ??? ?? ?????. 

    Canary? ?? ???? ?? ???? ???? ???????. 85,000?? ??? ??? ??? ???? ?? ??? ?????. Canary? ??? ???? ?? NVIDIA NeMo ??? ?? ??? ???? ???? ?? ??? ?? ????? ??? ??????. 

    Canary? ?? ?? ?? ???? ????? ???? ?? ? ?? ?? ? ??? ??? ??? Whisper-large-v3 ? SeamlessM4T-Medium-v1 ??? ?????. ??, ????, ????, ???? MCV 16.1 ??? ???? Canary? WER? 5.77?????(?? 1).

    ?? 1. MCV 16.1 ??? ??? ?? ?? ???(WER)
    (???? ??)

    Gradio ???? canary-1b ??? ??? ? ? ????. ???? Canary? ????? ? ?? ???? ??? ?? ??? ????NVIDIA/NeMo?GitHub ?????? ?????.

    Canary ????

    Canary? NVIDIA ??? ???? ??? ???-??? ?????. 

    ???? ??? ??? ?? 3?, ???? ?? 4? ????? ???? ???? Conformer ???? Fast-Conformer???. ???? ??-? ?????? ??? ??? ???? ????, ????? ???? ?? ?? ???? ?? ??? ??? ?????. Canary? ??? ?? ? ??? ???? ???? ?? ??? ???? ??? ????. 

    ?? Canary? ??? ?????? ???? ?? ?? ??? ????? ?????.?

    ?? ???? ?? ???? ???? CC BY-NC 4.0 ????? ?? ????, ? ??? ???? ? ???? ???NeMo? Apache 2.0 ????? ?? ?? ?????. 

    Canary? ???? ??

    Canary? ????? NeMo? pip ???? ???? ???. NeMo? ???? ? Cython ? PyTorch(2.0 ??)? ?????. 

    pip install nemo_toolkit['asr']

    NeMo? ???? Canary? ???? ??? ??? ????? ?????. 

    # Load Canary model
    from nemo.collections.asr.models import EncDecMultiTaskModel
    canary_model = EncDecMultiTaskModel.from_pretrained('nvidia/canary-1b')
      
    # Transcribe
    transcript = canary_model.transcribe(audio=["path_to_audio_file.wav"])
    # By default, Canary assumes that input audio is in English and transcribes it.
     
    # To transcribe in a different language, such as Spanish
    transcript = canary_model.transcribe(
         audio=["path_to_spanish_audio_file.wav"],
         batch_size=1,
         task='asr',
         source_lang='es',  # es: Spanish, fr: French, de: German
         target_lang='es',  # should be same as "source_lang" for 'asr'
         pnc=True )
     
    # To translate using Canary. For example, from English audio to French text
    transcript = canary_model.transcribe(
         audio=["path_to_english_audio_file.wav"],
         batch_size=1,
         task='ast',
         source_lang='en',
         target_lang='fr',  
         pnc=True )

    ??

    Canary ??? ??? ??, ????, ???, ?????? ??? ?? ?? ? ??? ???? ??? ???? ??????.

    Canary ????? ?? ??? ??? ?? ???? ????? ????.

    Gradio ????? ??canary-1b? ??? ??? NVIDIA/NeMoGitHub ?????? ?? ??? ??? ??????. Parakeet-CTC? ?? ?? ???? ?? ??? NVIDIA Riva? ??? ? ??? ?????. 

    NVIDIA API ????? ?? AI ??? ??? ?? NVIDIA NIM? ?? ??????? ?????. ?? ??? ?? NVIDIA LaunchPad? ???? ??? ???? ??? ???? ? ????? ??? ?????.

    ?? ?? ??

    ? ???? ??? ?? ?? ?????? ??????.?Krishna Puvvada, Piotr Zelasko, He Huang, (Steve) Oleksii Hrinchuk, Nithin Koluguri, Somshubra Majumdar, Elena Rastorgueva, Kunal Dhawan, Zhehuai Chen, Vitaly Lavrukhin, Jagadeesh Balam, Boris G

    ?? ???

    GTC ??: ??? ??? ????? ?? ?? ?? ????????(NVIDIA NeMo)
    GTC ??: ???? ??? ?? ??(PEFT)? ??? ?? ?? ?? ?? ??
    GTC ??: NVIDIA NeMo ? AWS? ??? LLM ???? ???
    NGC ????: ???? NeMo ASR ??????
    SDK: NeMo ????
    SDK: NeMo

    Discuss (0)
    +2

    Tags

    人人超碰97caoporen国产