search

m-bain / whisperX

WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)
BSD 2-Clause "Simplified" License
12.58k stars 1.33k forks source link

Translate japanese audio #824

Open sansan14102 opened 5 months ago

sansan14102 commented 5 months ago

When I use whisperx to transcribe and translate japanese audio, I got very long text with long duration.

I probably do something wrong. I am using the following command, but it doesn't work.

whisperx --model large-v2 --language ja --compute_type float32 --align_model WAV2VEC2_ASR_LARGE_LV60K_960H --max_line_width 24 --max_line_count 2 --task translate --output_format srt audio.wav

thanks.

jim60105 commented 5 months ago

--chunk_size 10