Whisper: Support command line

[madroidmaq]

sample:

mlx_whisper audio.mp3 \
        --model mlx-community/whisper-large-v3-mlx-8bit \
        --output_format all \
        --word_timestamps True \
        --verbose True

output files:

audio.json
audio.srt
audio.tsv
audio.txt
audio.vtt

for more details ues mlx_whisper --help

mlx_whisper --help
usage: cli.py [-h] [--model MODEL] [--output_dir OUTPUT_DIR] [--output_format {txt,vtt,srt,tsv,json,all}] [--verbose VERBOSE] [--task {transcribe,translate}]
              [--language {af,am,ar,as,az,ba,be,bg,bn,bo,br,bs,ca,cs,cy,da,de,el,en,es,et,eu,fa,fi,fo,fr,gl,gu,ha,haw,he,hi,hr,ht,hu,hy,id,is,it,ja,jw,ka,kk,km,kn,ko,la,lb,ln,lo,lt,lv,mg,mi,mk,ml,mn,mr,ms,mt,my,ne,nl,nn,no,oc,pa,pl,ps,pt,ro,ru,sa,sd,si,sk,sl,sn,so,sq,sr,su,sv,sw,ta,te,tg,th,tk,tl,tr,tt,uk,ur,uz,vi,yi,yo,yue,zh,Afrikaans,Albanian,Amharic,Arabic,Armenian,Assamese,Azerbaijani,Bashkir,Basque,Belarusian,Bengali,Bosnian,Breton,Bulgarian,Burmese,Cantonese,Castilian,Catalan,Chinese,Croatian,Czech,Danish,Dutch,English,Estonian,Faroese,Finnish,Flemish,French,Galician,Georgian,German,Greek,Gujarati,Haitian,Haitian Creole,Hausa,Hawaiian,Hebrew,Hindi,Hungarian,Icelandic,Indonesian,Italian,Japanese,Javanese,Kannada,Kazakh,Khmer,Korean,Lao,Latin,Latvian,Letzeburgesch,Lingala,Lithuanian,Luxembourgish,Macedonian,Malagasy,Malay,Malayalam,Maltese,Mandarin,Maori,Marathi,Moldavian,Moldovan,Mongolian,Myanmar,Nepali,Norwegian,Nynorsk,Occitan,Panjabi,Pashto,Persian,Polish,Portuguese,Punjabi,Pushto,Romanian,Russian,Sanskrit,Serbian,Shona,Sindhi,Sinhala,Sinhalese,Slovak,Slovenian,Somali,Spanish,Sundanese,Swahili,Swedish,Tagalog,Tajik,Tamil,Tatar,Telugu,Thai,Tibetan,Turkish,Turkmen,Ukrainian,Urdu,Uzbek,Valencian,Vietnamese,Welsh,Yiddish,Yoruba}]
              [--temperature TEMPERATURE] [--best_of BEST_OF] [--patience PATIENCE] [--length_penalty LENGTH_PENALTY] [--suppress_tokens SUPPRESS_TOKENS] [--initial_prompt INITIAL_PROMPT]
              [--condition_on_previous_text CONDITION_ON_PREVIOUS_TEXT] [--fp16 FP16] [--compression_ratio_threshold COMPRESSION_RATIO_THRESHOLD] [--logprob_threshold LOGPROB_THRESHOLD]
              [--no_speech_threshold NO_SPEECH_THRESHOLD] [--word_timestamps WORD_TIMESTAMPS] [--prepend_punctuations PREPEND_PUNCTUATIONS] [--append_punctuations APPEND_PUNCTUATIONS]
              [--highlight_words HIGHLIGHT_WORDS] [--max_line_width MAX_LINE_WIDTH] [--max_line_count MAX_LINE_COUNT] [--max_words_per_line MAX_WORDS_PER_LINE]
              [--clip_timestamps CLIP_TIMESTAMPS] [--hallucination_silence_threshold HALLUCINATION_SILENCE_THRESHOLD]
              audio [audio ...]

positional arguments:
  audio                 audio file(s) to transcribe

options:
  -h, --help            show this help message and exit
  --model MODEL         the path to save model files, or the hugging face repo id to use (default: mlx-community/whisper-tiny)
  --output_dir OUTPUT_DIR, -o OUTPUT_DIR
                        directory to save the outputs (default: .)
  --output_format {txt,vtt,srt,tsv,json,all}, -f {txt,vtt,srt,tsv,json,all}
                        format of the output file; if not specified, all available formats will be produced (default: all)
  --verbose VERBOSE     whether to print out the progress and debug messages (default: True)
  --task {transcribe,translate}
                        whether to perform X->X speech recognition ('transcribe') or X->English translation ('translate') (default: transcribe)
  --language {af,am,ar,as,az,ba,be,bg,bn,bo,br,bs,ca,cs,cy,da,de,el,en,es,et,eu,fa,fi,fo,fr,gl,gu,ha,haw,he,hi,hr,ht,hu,hy,id,is,it,ja,jw,ka,kk,km,kn,ko,la,lb,ln,lo,lt,lv,mg,mi,mk,ml,mn,mr,ms,mt,my,ne,nl,nn,no,oc,pa,pl,ps,pt,ro,ru,sa,sd,si,sk,sl,sn,so,sq,sr,su,sv,sw,ta,te,tg,th,tk,tl,tr,tt,uk,ur,uz,vi,yi,yo,yue,zh,Afrikaans,Albanian,Amharic,Arabic,Armenian,Assamese,Azerbaijani,Bashkir,Basque,Belarusian,Bengali,Bosnian,Breton,Bulgarian,Burmese,Cantonese,Castilian,Catalan,Chinese,Croatian,Czech,Danish,Dutch,English,Estonian,Faroese,Finnish,Flemish,French,Galician,Georgian,German,Greek,Gujarati,Haitian,Haitian Creole,Hausa,Hawaiian,Hebrew,Hindi,Hungarian,Icelandic,Indonesian,Italian,Japanese,Javanese,Kannada,Kazakh,Khmer,Korean,Lao,Latin,Latvian,Letzeburgesch,Lingala,Lithuanian,Luxembourgish,Macedonian,Malagasy,Malay,Malayalam,Maltese,Mandarin,Maori,Marathi,Moldavian,Moldovan,Mongolian,Myanmar,Nepali,Norwegian,Nynorsk,Occitan,Panjabi,Pashto,Persian,Polish,Portuguese,Punjabi,Pushto,Romanian,Russian,Sanskrit,Serbian,Shona,Sindhi,Sinhala,Sinhalese,Slovak,Slovenian,Somali,Spanish,Sundanese,Swahili,Swedish,Tagalog,Tajik,Tamil,Tatar,Telugu,Thai,Tibetan,Turkish,Turkmen,Ukrainian,Urdu,Uzbek,Valencian,Vietnamese,Welsh,Yiddish,Yoruba}
                        language spoken in the audio, specify None to perform language detection (default: None)
  --temperature TEMPERATURE
                        temperature to use for sampling (default: 0)
  --best_of BEST_OF     number of candidates when sampling with non-zero temperature (default: 5)
  --patience PATIENCE   optional patience value to use in beam decoding, as in https://arxiv.org/abs/2204.05424, the default (1.0) is equivalent to conventional beam search (default: None)
  --length_penalty LENGTH_PENALTY
                        optional token length penalty coefficient (alpha) as in https://arxiv.org/abs/1609.08144, uses simple length normalization by default (default: None)
  --suppress_tokens SUPPRESS_TOKENS
                        comma-separated list of token ids to suppress during sampling; '-1' will suppress most special characters except common punctuations (default: -1)
  --initial_prompt INITIAL_PROMPT
                        optional text to provide as a prompt for the first window. (default: None)
  --condition_on_previous_text CONDITION_ON_PREVIOUS_TEXT
                        if True, provide the previous output of the model as a prompt for the next window; disabling may make the text inconsistent across windows, but the model becomes less
                        prone to getting stuck in a failure loop (default: True)
  --fp16 FP16           whether to perform inference in fp16; True by default (default: True)
  --compression_ratio_threshold COMPRESSION_RATIO_THRESHOLD
                        if the gzip compression ratio is higher than this value, treat the decoding as failed (default: 2.4)
  --logprob_threshold LOGPROB_THRESHOLD
                        if the average log probability is lower than this value, treat the decoding as failed (default: -1.0)
  --no_speech_threshold NO_SPEECH_THRESHOLD
                        if the probability of the <|nospeech|> token is higher than this value AND the decoding has failed due to `logprob_threshold`, consider the segment as silence (default:
                        0.6)
  --word_timestamps WORD_TIMESTAMPS
                        (experimental) extract word-level timestamps and refine the results based on them (default: False)
  --prepend_punctuations PREPEND_PUNCTUATIONS
                        if word_timestamps is True, merge these punctuation symbols with the next word (default: "'“¿([{-)
  --append_punctuations APPEND_PUNCTUATIONS
                        if word_timestamps is True, merge these punctuation symbols with the previous word (default: "'.。,，!！?？:：”)]}、)
  --highlight_words HIGHLIGHT_WORDS
                        (requires --word_timestamps True) underline each word as it is spoken in srt and vtt (default: False)
  --max_line_width MAX_LINE_WIDTH
                        (requires --word_timestamps True) the maximum number of characters in a line before breaking the line (default: None)
  --max_line_count MAX_LINE_COUNT
                        (requires --word_timestamps True) the maximum number of lines in a segment (default: None)
  --max_words_per_line MAX_WORDS_PER_LINE
                        (requires --word_timestamps True, no effect with --max_line_width) the maximum number of words in a segment (default: None)
  --clip_timestamps CLIP_TIMESTAMPS
                        comma-separated list start,end,start,end,... timestamps (in seconds) of clips to process, where the last end timestamp defaults to the end of the file (default: 0)
  --hallucination_silence_threshold HALLUCINATION_SILENCE_THRESHOLD
                        (requires --word_timestamps True) skip silent periods longer than this threshold (in seconds) when a possible hallucination is detected (default: None)

[madroidmaq]

I implemented it with reference to the openai whisper project and tested most of the command parameters (such as task、output_format、word_timestamps), but not all of them.

https://github.com/openai/whisper/blob/ba3f3cd54b0e5b8ce1ab3de13e32122d0d5f98ab/whisper/transcribe.py#L501

[awni]

I'm not sure I get the purpose of these. Shouldn't argparse handle the default=None case correctly already?

[awni]

Also what is the purpose of this.. why not just use type=bool in the argparse argument?

[awni]

This looks really nice. I left a couple minor comments. Could you please check? After that I think we can merge it. Thanks for the addition!

[awni]

Most of our CLI tools use - instead of _. For consistency I would suggest we do the same for the arguments here. Or did you get this from the original Whisper implementation? Maybe it is good to be consistent with that if so?