metadata

language:
  - en
  - zh
  - de
  - es
  - ru
  - ko
  - fr
  - ja
  - pt
  - tr
  - pl
  - ca
  - nl
  - ar
  - sv
  - it
  - id
  - hi
  - fi
  - vi
  - he
  - uk
  - el
  - ms
  - cs
  - ro
  - da
  - hu
  - ta
  - 'no'
  - th
  - ur
  - hr
  - bg
  - lt
  - la
  - mi
  - ml
  - cy
  - sk
  - te
  - fa
  - lv
  - bn
  - sr
  - az
  - sl
  - kn
  - et
  - mk
  - br
  - eu
  - is
  - hy
  - ne
  - mn
  - bs
  - kk
  - sq
  - sw
  - gl
  - mr
  - pa
  - si
  - km
  - sn
  - yo
  - so
  - af
  - oc
  - ka
  - be
  - tg
  - sd
  - gu
  - am
  - yi
  - lo
  - uz
  - fo
  - ht
  - ps
  - tk
  - nn
  - mt
  - sa
  - lb
  - my
  - bo
  - tl
  - mg
  - as
  - tt
  - haw
  - ln
  - ha
  - ba
  - jw
  - su
tags:
  - audio
  - automatic-speech-recognition
license: mit
library_name: ctranslate2

Whisper large-v3-turbo model for CTranslate2

This repository contains the conversion of openai/whisper-large-v3-turbo to the CTranslate2 model format.

This model can be used in CTranslate2 or projects based on CTranslate2 such as faster-whisper.

Example with batch inference

import time

from faster_whisper import WhisperModel, BatchedInferencePipeline
from faster_whisper.audio import decode_audio

model = WhisperModel("Infomaniak-AI/faster-whisper-large-v3-turbo",
                     device="cuda",
                     num_workers=4,
                     compute_type='float16')

batch = BatchedInferencePipeline(model=model,
                                 use_vad_model=True,
                                 chunk_length=30)

audio = decode_audio("audio.mp3", sampling_rate=model.feature_extractor.sampling_rate)
start_time = time.time()
segment_generator, info = batch.transcribe(audio,
                                           batch_size=32,
                                           beam_size=5,
                                           task="transcribe",
                                           word_timestamps=True,
                                           suppress_blank=True)
segments = []
text = ""
for segment in segment_generator:
    segments.append(segment)
    text = text + segment.text

print("--- %s seconds ---" % (time.time() - start_time))

Conversion details

The original model was converted with the following command:

ct2-transformers-converter --model openai/whisper-large-v3-turbo --output_dir whisper-large-v3-turbo --copy_files tokenizer.json preprocessor_config.json --quantization float16

Note that the model weights are saved in FP16. This type can be changed when the model is loaded using the compute_type option in CTranslate2.

More information

For more information about the original model, see its model card.