Closed abdelazizSalah closed 5 months ago
I managed to download the small.pt model, and cloned the repo at the shown path, however
on executing this command:
"python3 models/convert-pt-to-ggml.py /Users/zizo/Downloads/small.pt /Users/zizo/Documents/GitHub/whisper.cpp ./models/whisper-medium"
I get the following error:
hparams: {'n_mels': 80, 'n_vocab': 51865, 'n_audio_ctx': 1500, 'n_audio_state': 768, 'n_audio_head': 12, 'n_audio_layer': 12, 'n_text_ctx': 448, 'n_text_state': 768, 'n_text_head': 12, 'n_text_layer': 12} Traceback (most recent call last): File "/Users/zizo/Documents/GitHub/whisper.cpp/models/convert-pt-to-ggml.py", line 221, in with np.load(dir_whisper / "whisper" / "assets" / "mel_filters.npz") as f: File "/Users/zizo/Library/Python/3.9/lib/python/site-packages/numpy/lib/npyio.py", line 427, in load fid = stack.enter_context(open(os_fspath(file), "rb")) FileNotFoundError: [Errno 2] No such file or directory: '/Users/zizo/Documents/GitHub/whisper.cpp/whisper/assets/mel_filters.npz'
And I have looked for the folder /whisper but I did not find it, and I did not also find the file Mel_filters.npz.
So do anyone have any idea how to resolve this to be able to load the model and start using the demo?
You need to clone the OpenAI Whisper repo to get the mel filter assets: https://github.com/openai/whisper/tree/main/whisper/assets
it worked thanks!!
I managed to download the small.pt model, and cloned the repo at the shown path, however
on executing this command:
I get the following error:
And I have looked for the folder /whisper but I did not find it, and I did not also find the file Mel_filters.npz.
So do anyone have any idea how to resolve this to be able to load the model and start using the demo?