Wav2vec2 Xls R 1b French

🚀 Fine-tuned XLS-R 1B model for speech recognition in French

This is a fine-tuned model based on facebook/wav2vec2-xls-r-1b for French speech recognition, which provides high - quality speech recognition capabilities.

🚀 Quick Start

This model is fine - tuned on French using the train and validation splits of Common Voice 8.0, MediaSpeech, Multilingual TEDx, Multilingual LibriSpeech, and Voxpopuli. When using this model, make sure that your speech input is sampled at 16kHz.

This model has been fine - tuned by the HuggingSound tool, and thanks to the GPU credits generously given by the OVHcloud.

✨ Features

• Language Support: Specifically designed for French speech recognition.
• Fine - Tuned Data: Utilizes multiple high - quality datasets for fine - tuning.
• Tools and Credits: Fine - tuned with HuggingSound and supported by OVHcloud GPU credits.

💻 Usage Examples

Basic Usage

Using the HuggingSound library:

from huggingsound import SpeechRecognitionModel

model = SpeechRecognitionModel("jonatasgrosman/wav2vec2-xls-r-1b-french")
audio_paths = ["/path/to/file.mp3", "/path/to/another_file.wav"]

transcriptions = model.transcribe(audio_paths)

Advanced Usage

Writing your own inference script:

import torch
import librosa
from datasets import load_dataset
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor

LANG_ID = "fr"
MODEL_ID = "jonatasgrosman/wav2vec2-xls-r-1b-french"
SAMPLES = 10

test_dataset = load_dataset("common_voice", LANG_ID, split=f"test[:{SAMPLES}]")

processor = Wav2Vec2Processor.from_pretrained(MODEL_ID)
model = Wav2Vec2ForCTC.from_pretrained(MODEL_ID)

# Preprocessing the datasets.
# We need to read the audio files as arrays
def speech_file_to_array_fn(batch):
    speech_array, sampling_rate = librosa.load(batch["path"], sr=16_000)
    batch["speech"] = speech_array
    batch["sentence"] = batch["sentence"].upper()
    return batch

test_dataset = test_dataset.map(speech_file_to_array_fn)
inputs = processor(test_dataset["speech"], sampling_rate=16_000, return_tensors="pt", padding=True)

with torch.no_grad():
    logits = model(inputs.input_values, attention_mask=inputs.attention_mask).logits

predicted_ids = torch.argmax(logits, dim=-1)
predicted_sentences = processor.batch_decode(predicted_ids)

📚 Documentation

Evaluation Commands

1. To evaluate on mozilla-foundation/common_voice_8_0 with split test

python eval.py --model_id jonatasgrosman/wav2vec2-xls-r-1b-french --dataset mozilla-foundation/common_voice_8_0 --config fr --split test

2. To evaluate on speech-recognition-community-v2/dev_data

python eval.py --model_id jonatasgrosman/wav2vec2-xls-r-1b-french --dataset speech-recognition-community-v2/dev_data --config fr --split validation --chunk_length_s 5.0 --stride_length_s 1.0

Model Information

Results

The model named "XLS - R Wav2Vec2 French by Jonatas Grosman" has the following performance metrics:

📄 License

This model is under the Apache - 2.0 license.

📚 Citation

If you want to cite this model you can use this:

@misc{grosman2021xlsr-1b-french,
  title={Fine-tuned {XLS-R} 1{B} model for speech recognition in {F}rench},
  author={Grosman, Jonatas},
  howpublished={\url{https://huggingface.co/jonatasgrosman/wav2vec2-xls-r-1b-french}},
  year={2022}
}