Wav2Vec2-Large-XLSR-53-Basque

Fine-tuned facebook/wav2vec2-large-xlsr-53 in Basque using the Common Voice. When using this model, make sure that your speech input is sampled at 16kHz.

Usage

The model can be used directly (without a language model) as follows:


import torch

import torchaudio

from datasets import load_dataset

from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor

test_dataset = load_dataset("common_voice", "eu", split="test[:2%]").

processor = Wav2Vec2Processor.from_pretrained("stefan-it/wav2vec2-large-xlsr-53-basque")

model = Wav2Vec2ForCTC.from_pretrained("stefan-it/wav2vec2-large-xlsr-53-basque")

resampler = torchaudio.transforms.Resample(48_000, 16_000)

# Preprocessing the datasets.

# We need to read the aduio files as arrays

def speech_file_to_array_fn(batch):

  speech_array, sampling_rate = torchaudio.load(batch["path"])

  batch["speech"] = resampler(speech_array).squeeze().numpy()

  return batch

test_dataset = test_dataset.map(speech_file_to_array_fn)

inputs = processor(test_dataset["speech"][:2], 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)

print("Prediction:", processor.batch_decode(predicted_ids))

print("Reference:", test_dataset["sentence"][:2])

Evaluation

The model can be evaluated as follows on the Basque test data of Common Voice.


import torch

import torchaudio

from datasets import load_dataset, load_metric

from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor

import re

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

wer = load_metric("wer")

processor = Wav2Vec2Processor.from_pretrained("stefan-it/wav2vec2-large-xlsr-53-basque")

model = Wav2Vec2ForCTC.from_pretrained("stefan-it/wav2vec2-large-xlsr-53-basque")

model.to("cuda")

chars_to_ignore_regex = '[\\\\,\\\\?\\\\.\\\\!\\\\-\\\\;\\\\:\\\\"\\\\“\\\\%\\\\‘\\\\”\\\\�]'

resampler = torchaudio.transforms.Resample(48_000, 16_000)

# Preprocessing the datasets.

# We need to read the aduio files as arrays

def speech_file_to_array_fn(batch):

  batch["sentence"] = re.sub(chars_to_ignore_regex, '', batch["sentence"]).lower()

  speech_array, sampling_rate = torchaudio.load(batch["path"])

  batch["speech"] = resampler(speech_array).squeeze().numpy()

  return batch

test_dataset = test_dataset.map(speech_file_to_array_fn)

# Preprocessing the datasets.

# We need to read the aduio 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("cuda"), attention_mask=inputs.attention_mask.to("cuda")).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)

print("WER: {:2f}".format(100 * wer.compute(predictions=result["pred_strings"], references=result["sentence"])))

Test Result: 18.272625%

Training

The Common Voice train, validation datasets were used for training.

The script used for training can be found here, hopefully very soon!

Acknowledgements

Many thanks to the OVH team for providing access to a V-100 instance. Without their help, fine-tuning would not be possible!

I would also thank Manuel Romero (mrm8488) for helping with the fine-tuning script!

Downloads last month
20
Hosted inference API
Automatic Speech Recognition
or
This model can be loaded on the Inference API on-demand.
Evaluation results