Wav2vec2 Xls R 1b Spanish

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

This is a fine-tuned model for Spanish speech recognition. It is based on facebook/wav2vec2-xls-r-1b and fine-tuned using the train and validation splits of multiple datasets, including Common Voice 8.0, MediaSpeech, Multilingual TEDx, Multilingual LibriSpeech, and Voxpopuli. When using this model, ensure that your speech input is sampled at 16kHz.

✨ Features

• Language Support: Specifically fine-tuned for Spanish speech recognition.
• Multiple Datasets: Trained on a variety of datasets for better generalization.
• Performance Metrics: Achieved good results on multiple evaluation datasets, including low WER (Word Error Rate) and CER (Character Error Rate).

📦 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-xls-r-1b-spanish")
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 = "es"
MODEL_ID = "jonatasgrosman/wav2vec2-xls-r-1b-spanish"
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-spanish --dataset mozilla-foundation/common_voice_8_0 --config es --split test

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

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

Model Information

📄 License

This model is licensed under the Apache-2.0 license.

📚 Citation

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

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