Wav2vec2 Large Fr Voxpopuli French

🚀 Fine-tuned French Voxpopuli wav2vec2 large model for speech recognition in French

This model is fine-tuned from facebook/wav2vec2-large-fr-voxpopuli on French, aiming to provide high - quality speech recognition service.

🚀 Quick Start

The model is fine - tuned from facebook/wav2vec2-large-fr-voxpopuli on French using the train and validation splits of Common Voice 6.1. When using this model, make sure that your speech input is sampled at 16kHz.

This model has been fine - tuned thanks to the GPU credits generously given by the OVHcloud :)

The script used for training can be found here: https://github.com/jonatasgrosman/wav2vec2-sprint

✨ Features

• Dataset: Fine - tuned on the French part of Common Voice 6.1.
• Metrics: Evaluated by Word Error Rate (WER) and Character Error Rate (CER).
• Compatibility: Requires speech input sampled at 16kHz.

📦 Installation

No specific installation steps are provided in the original document.

💻 Usage Examples

Basic Usage

Using the HuggingSound library:

from huggingsound import SpeechRecognitionModel

model = SpeechRecognitionModel("jonatasgrosman/wav2vec2-large-fr-voxpopuli-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-large-fr-voxpopuli-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)

for i, predicted_sentence in enumerate(predicted_sentences):
    print("-" * 100)
    print("Reference:", test_dataset[i]["sentence"])
    print("Prediction:", predicted_sentence)

Usage Example Table

📚 Documentation

Evaluation

The model can be evaluated as follows on the French (fr) test data of Common Voice.

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

LANG_ID = "fr"
MODEL_ID = "jonatasgrosman/wav2vec2-large-fr-voxpopuli-french"
DEVICE = "cuda"

CHARS_TO_IGNORE = [",", "?", "¿", ".", "!", "¡", ";", "；", ":", '""', "%", '"', "�", "ʿ", "·", "჻", "~", "՞",
                   "؟", "،", "।", "॥", "«", "»", "„", "“", "”", "「", "」", "‘", "’", "《", "》", "(", ")", "[", "]",
                   "{", "}", "=", "`", "_", "+", "<", ">", "…", "–", "°", "´", "ʾ", "‹", "›", "©", "®", "—", "→", "。",
                   "、", "﹂", "﹁", "‧", "～", "﹏", "，", "｛", "｝", "（", "）", "［", "］", "【", "】", "‥", "〽",
                   "『", "』", "〝", "〟", "⟨", "⟩", "〜", "：", "！", "？", "♪", "؛", "/", "\\", "º", "−", "^", "ʻ", "ˆ"]

test_dataset = load_dataset("common_voice", LANG_ID, split="test")

wer = load_metric("wer.py") # https://github.com/jonatasgrosman/wav2vec2-sprint/blob/main/wer.py
cer = load_metric("cer.py") # https://github.com/jonatasgrosman/wav2vec2-sprint/blob/main/cer.py

chars_to_ignore_regex = f"[{re.escape(''.join(CHARS_TO_IGNORE))}]"

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

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

test_dataset = test_dataset.map(speech_file_to_array_fn)

# Preprocessing the datasets.
# We need to read the audio files as arrays
def evaluate(batch):
    inputs = processor(batch["speech"], sampling_rate=16_000, return_tensors="pt", padding=True)

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

    pred_ids = torch.argmax(logits, dim=-1)
    batch["pred_strings"] = processor.batch_decode(pred_ids)
    return batch

result = test_dataset.map(evaluate, batched=True, batch_size=8)

predictions = [x.upper() for x in result["pred_strings"]]
references = [x.upper() for x in result["sentence"]]

print(f"WER: {wer.compute(predictions=predictions, references=references, chunk_size=1000) * 100}")
print(f"CER: {cer.compute(predictions=predictions, references=references, chunk_size=1000) * 100}")

Test Result

In the table below I report the Word Error Rate (WER) and the Character Error Rate (CER) of the model. I ran the evaluation script described above on other models as well (on 2021 - 05 - 16). Note that the table below may show different results from those already reported, this may have been caused due to some specificity of the other evaluation scripts used.

📄 License

The model is released under the apache - 2.0 license.

📚 Model Index

📚 Citation

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

@misc{grosman2021voxpopuli-fr-wav2vec2-large-french,
  title={Fine-tuned {F}rench {V}oxpopuli wav2vec2 large model for speech recognition in {F}rench},
  author={Grosman, Jonatas},
  howpublished={\url{https://huggingface.co/jonatasgrosman/wav2vec2-large-fr-voxpopuli-french}},
  year={2021}
}