← Back to context

Comment by jokethrowaway

10 days ago

whisper is definitely nice, but it's a bit too slow. Having subtitles and transcription for everything is great - but Nemo Parakeet (pretty much whisper by nvidia) completely changed how I interact with the computer.

It enables dictation that actually works and it's as fast as you can think. I also have a set of scripts which just wait for voice commands and do things. I can pipe the results to an LLM, run commands, synthesize a voice with F5-TTS back and it's like having a local Jarvis.

The main limitation is being english only.

5 comments

jokethrowaway

Reply
forgingahead  10 days ago

Yeah, mind sharing any of the scripts? I looked at the docs briefly, looks like we need to install ALL of nemo to get access to Parakeet? Seems ultra heavy.

  • rhdunn  10 days ago

    You only need the ASR bits -- this is where I got to when I previously looked into running Parakeet:

        # NeMo does not run on 3.13+
    python3.12 -m venv .venv
    source .venv/bin/activate

    git clone https://github.com/NVIDIA/NeMo.git nemo
    cd nemo

    pip install torch torchaudio torchvision --index-url https://download.pytorch.org/whl/cu128
    pip install .[asr]

    deactivate

    Then run a transcribe.py script in that venv:

        import os
    import sys
    import nemo.collections.asr as nemo_asr

    model_path = sys.argv[1]
    audio_path = sys.argv[2]

    # Load from a local path...
    asr_model = nemo_asr.models.EncDecRNNTBPEModel.restore_from(restore_path=model_path)

    # Or download from huggingface ('org/model')...
    asr_model = nemo_asr.models.EncDecRNNTBPEModel.from_pretrained(model_name=model_path)

    output = asr_moel.transcribe([audio_path])
    print(output[0])

    With that I was able to run the model, but I ran out of memory on my lower-spec laptop. I haven't yet got around to running it on my workstation.

    You'll need to modify the python script to process the response and output it in a format you can use.