Wav2vec2 Large Xlsr 53 Portuguese

🚀 Fine-tuned XLSR-53 large model for speech recognition in Portuguese

This model is a fine - tuned version of facebook/wav2vec2-large-xlsr-53 on Portuguese, using the train and validation splits of Common Voice 6.1. It provides high - quality speech recognition for Portuguese.

📦 Information Table

🚀 Quick Start

This fine - tuned model is based on facebook/wav2vec2-large-xlsr-53 and trained on Portuguese 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

💻 Usage Examples

Basic Usage

Using the HuggingSound library:

from huggingsound import SpeechRecognitionModel

model = SpeechRecognitionModel("jonatasgrosman/wav2vec2-large-xlsr-53-portuguese")
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 = "pt"
MODEL_ID = "jonatasgrosman/wav2vec2-large-xlsr-53-portuguese"
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)

Here is a comparison table of reference and prediction:

🔧 Evaluation

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

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

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

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

📄 License

This model is under the Apache - 2.0 license.

📚 Citation

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

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