Wav2vec2 Large Xlsr 53 Dutch

🚀 Wav2Vec2-Large-XLSR-53-Dutch

This model is fine-tuned from facebook/wav2vec2-large-xlsr-53 on Dutch using the Common Voice dataset. It's designed for automatic speech recognition tasks in Dutch.

📋 Metadata

📊 Model Index

• Name: Dutch XLSR Wav2Vec2 Large 53 by Wietse de Vries
• Results:
  • Task:
    • Name: Speech Recognition
    • Type: automatic-speech-recognition
  • Dataset:
    • Name: Common Voice nl
    • Type: common_voice
    • Args: nl
  • Metrics:
    • Name: Test WER
    • Type: wer
    • Value: 17.09

🚀 Quick Start

When using this model, make sure that your speech input is sampled at 16kHz.

💻 Usage Examples

Basic Usage

import torch
import torchaudio
from datasets import load_dataset
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor

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

processor = Wav2Vec2Processor.from_pretrained("wietsedv/wav2vec2-large-xlsr-53-dutch")
model = Wav2Vec2ForCTC.from_pretrained("wietsedv/wav2vec2-large-xlsr-53-dutch")

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 Dutch 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", "nl", split="test")
wer = load_metric("wer")

processor = Wav2Vec2Processor.from_pretrained("wietsedv/wav2vec2-large-xlsr-53-dutch")
model = Wav2Vec2ForCTC.from_pretrained("wietsedv/wav2vec2-large-xlsr-53-dutch")
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: 17.09 %

🏋️‍♂️ Training

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

📄 License

This model is licensed under the apache-2.0 license.