Wav2vec2 Large Xlsr 53 English

🚀 XLSR Wav2Vec2 English by Jonatas Grosman

This project presents a fine - tuned XLSR - 53 large model for English speech recognition. It addresses the need for accurate automatic speech recognition in English, leveraging pre - trained models and fine - tuning on specific datasets to achieve high - quality results.

🚀 Quick Start

This model is a fine - tuned version of facebook/wav2vec2-large-xlsr-53 on English, using the train and validation splits of Common Voice 6.1. When using this model, ensure 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

• Datasets: Utilizes common_voice and mozilla - foundation/common_voice_6_0 for training and evaluation.
• Metrics: Evaluated using Word Error Rate (WER) and Character Error Rate (CER).
• Task: Focuses on the Automatic Speech Recognition task.

📦 Installation

There is no specific installation command provided in the original README. However, to use the model, you need to install relevant libraries such as huggingsound, torch, librosa, datasets, and transformers. You can install them using pip:

pip install huggingsound torch librosa datasets transformers

💻 Usage Examples

Basic Usage

Using the HuggingSound library:

from huggingsound import SpeechRecognitionModel

model = SpeechRecognitionModel("jonatasgrosman/wav2vec2-large-xlsr-53-english")
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 = "en"
MODEL_ID = "jonatasgrosman/wav2vec2-large-xlsr-53-english"
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)

Prediction Results

📚 Documentation

Evaluation

1. To evaluate on mozilla - foundation/common_voice_6_0 with split test

python eval.py --model_id jonatasgrosman/wav2vec2-large-xlsr-53-english --dataset mozilla-foundation/common_voice_6_0 --config en --split test

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

python eval.py --model_id jonatasgrosman/wav2vec2-large-xlsr-53-english --dataset speech-recognition-community-v2/dev_data --config en --split validation --chunk_length_s 5.0 --stride_length_s 1.0

📄 License

This model is licensed under the apache - 2.0 license.

📚 Model Index

Results

📖 Citation

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

@misc{grosman2021xlsr53-large-english,
  title={Fine-tuned {XLSR}-53 large model for speech recognition in {E}nglish},
  author={Grosman, Jonatas},
  howpublished={\url{https://huggingface.co/jonatasgrosman/wav2vec2-large-xlsr-53-english}},
  year={2021}
}