Whisper Large V2 French

🚀 Fine-tuned whisper-large-v2 model for ASR in French

This model is a fine - tuned version of openai/whisper-large-v2, designed for automatic speech recognition in French. It's trained on a large composite dataset of French speech audio, offering high - quality ASR performance.

🚀 Quick Start

This fine - tuned whisper-large-v2 model is ready to use for automatic speech recognition in French. When using the model, ensure that your speech input is sampled at 16Khz. Note that this model doesn't predict casing or punctuation.

✨ Features

• Fine - tuned: Based on the powerful openai/whisper-large-v2 model, fine - tuned on over 2200 hours of French speech audio.
• Multidataset training: Trained on a composite dataset including Common Voice 11.0, Multilingual LibriSpeech, and others.
• Low WER: Achieves low Word Error Rates (WER) on multiple French speech datasets.

📦 Installation

No specific installation steps are provided in the original document.

💻 Usage Examples

Basic Usage

Inference with 🤗 Pipeline

import torch

from datasets import load_dataset
from transformers import pipeline

device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")

# Load pipeline
pipe = pipeline("automatic-speech-recognition", model="bofenghuang/whisper-large-v2-french", device=device)

# NB: set forced_decoder_ids for generation utils
pipe.model.config.forced_decoder_ids = pipe.tokenizer.get_decoder_prompt_ids(language="fr", task="transcribe")

# Load data
ds_mcv_test = load_dataset("mozilla-foundation/common_voice_11_0", "fr", split="test", streaming=True)
test_segment = next(iter(ds_mcv_test))
waveform = test_segment["audio"]

# Run
generated_sentences = pipe(waveform, max_new_tokens=225)["text"]  # greedy
# generated_sentences = pipe(waveform, max_new_tokens=225, generate_kwargs={"num_beams": 5})["text"]  # beam search

# Normalise predicted sentences if necessary

Advanced Usage

Inference with 🤗 low - level APIs

import torch
import torchaudio

from datasets import load_dataset
from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq

device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")

# Load model
model = AutoModelForSpeechSeq2Seq.from_pretrained("bofenghuang/whisper-large-v2-french").to(device)
processor = AutoProcessor.from_pretrained("bofenghuang/whisper-large-v2-french", language="french", task="transcribe")

# NB: set forced_decoder_ids for generation utils
model.config.forced_decoder_ids = processor.get_decoder_prompt_ids(language="fr", task="transcribe")

# 16_000
model_sample_rate = processor.feature_extractor.sampling_rate

# Load data
ds_mcv_test = load_dataset("mozilla-foundation/common_voice_11_0", "fr", split="test", streaming=True)
test_segment = next(iter(ds_mcv_test))
waveform = torch.from_numpy(test_segment["audio"]["array"])
sample_rate = test_segment["audio"]["sampling_rate"]

# Resample
if sample_rate != model_sample_rate:
    resampler = torchaudio.transforms.Resample(sample_rate, model_sample_rate)
    waveform = resampler(waveform)

# Get feat
inputs = processor(waveform, sampling_rate=model_sample_rate, return_tensors="pt")
input_features = inputs.input_features
input_features = input_features.to(device)

# Generate
generated_ids = model.generate(inputs=input_features, max_new_tokens=225)  # greedy
# generated_ids = model.generate(inputs=input_features, max_new_tokens=225, num_beams=5)  # beam search

# Detokenize
generated_sentences = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]

# Normalise predicted sentences if necessary

📚 Documentation

Performance

Pre - trained models' WER

Below are the WERs of the pre - trained models on the Common Voice 9.0, Multilingual LibriSpeech, Voxpopuli and Fleurs. These results are reported in the original paper.

Fine - tuned models' WER

Below are the WERs of the fine - tuned models on the Common Voice 11.0, Multilingual LibriSpeech, Voxpopuli, and Fleurs. Note that these evaluation datasets have been filtered and preprocessed to only contain French alphabet characters and are removed of punctuation outside of apostrophe. The results in the table are reported as WER (greedy search) / WER (beam search with beam width 5).

📄 License

This model is licensed under the apache-2.0 license.