---
license: apache-2.0
language: fr
library_name: transformers
thumbnail: null
tags:
- automatic-speech-recognition
- hf-asr-leaderboard
- whisper-event
datasets:
- mozilla-foundation/common_voice_11_0
metrics:
- wer
model-index:
- name: Fine-tuned whisper-large-v2 model for ASR in French
  results:
  - task:
      name: Automatic Speech Recognition
      type: automatic-speech-recognition
    dataset:
      name: Common Voice 11.0
      type: mozilla-foundation/common_voice_11_0
      config: fr
      split: test
      args: fr
    metrics:
    - name: WER (Greedy)
      type: wer
      value: 8.05
    - name: WER (Beam 5)
      type: wer
      value: 7.67
  - task:
      name: Automatic Speech Recognition
      type: automatic-speech-recognition
    dataset:
      name: Multilingual LibriSpeech (MLS)
      type: facebook/multilingual_librispeech
      config: french
      split: test
      args: french
    metrics:
    - name: WER (Greedy)
      type: wer
      value: 5.56
    - name: WER (Beam 5)
      type: wer
      value: 5.28
  - task:
      name: Automatic Speech Recognition
      type: automatic-speech-recognition
    dataset:
      name: VoxPopuli
      type: facebook/voxpopuli
      config: fr
      split: test
      args: fr
    metrics:
    - name: WER (Greedy)
      type: wer
      value: 11.50
    - name: WER (Beam 5)
      type: wer
      value: 10.69
  - task:
      name: Automatic Speech Recognition
      type: automatic-speech-recognition
    dataset:
      name: Fleurs
      type: google/fleurs
      config: fr_fr
      split: test
      args: fr_fr
    metrics:
    - name: WER (Greedy)
      type: wer
      value: 5.42
    - name: WER (Beam 5)
      type: wer
      value: 5.05
  - task:
      name: Automatic Speech Recognition
      type: automatic-speech-recognition
    dataset:
      name: African Accented French
      type: gigant/african_accented_french
      config: fr
      split: test
      args: fr
    metrics:
    - name: WER (Greedy)
      type: wer
      value: 6.47
    - name: WER (Beam 5)
      type: wer
      value: 5.95
---

<style>
img {
 display: inline;
}
</style>

![Model architecture](https://img.shields.io/badge/Model_Architecture-seq2seq-lightgrey)
![Model size](https://img.shields.io/badge/Params-1550M-lightgrey)
![Language](https://img.shields.io/badge/Language-French-lightgrey)

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

This model is a fine-tuned version of [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2), trained on the mozilla-foundation/common_voice_11_0 fr dataset. When using the model make sure that your speech input is also sampled at 16Khz. **This model also predicts casing and punctuation.**

## Usage

Inference with 🤗 Pipeline

```python
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-cv11-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
```

Inference with 🤗 low-level APIs

```python
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-cv11-french").to(device)
processor = AutoProcessor.from_pretrained("bofenghuang/whisper-large-v2-cv11-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
```