not working on macOS

[mrveritas]

I've followed the instructions exactly but still can't transcribe audio file in a few minutes.

insanely-fast-whisper --file-name /[test].wav --device-id mps

🤗 Transcribing... ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 0:00:02You have passed task=transcribe, but also have set forced_decoder_ids to [[1, None], [2, 50360]] which creates a conflict. forced_decoder_ids will be ignored in favor of task=transcribe.
🤗 Transcribing... ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 0:00:17Passing a tuple of past_key_values is deprecated and will be removed in Transformers v4.43.0. You should pass an instance of EncoderDecoderCache instead, e.g. past_key_values=EncoderDecoderCache.from_legacy_cache(past_key_values).
🤗 Transcribing... ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 0:00:20The attention mask is not set and cannot be inferred from input because pad token is same as eos token. As a consequence, you may observe unexpected behavior. Please pass your input's attention_mask to obtain reliable results.
🤗 Transcribing... ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 0:00:46

it's getting stuck here and transcribing forever

[100xlongx]

same exact messages but not stuck, just slow

[bricolage]

I'm having the same issue. Command is insanely-fast-whisper --file-name test.mp3 --device-id mps --model-name distil-whisper/distil-large-v3 or insanely-fast-whisper --file-name test.mp3 --device-id mps --model-name openai/whisper-large-v3-turbo, with or without --batch-size 4

[scottinhawaii]

I get these too, but it works still. About 30 minutes for an 90 minute episode of a show.