faster-whisper-large-v3-turbo

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.