đ Wav2Vec2-Large-XLSR-53-Lithuanian
This model is a fine - tuned version of facebook/wav2vec2-large-xlsr-53 in Lithuanian, leveraging the Common Voice dataset. It's designed for automatic speech recognition tasks.
Dataset and Tags
- Datasets: common_voice
- Tags: audio, automatic-speech-recognition, speech, xlsr-fine-tuning-week
- License: apache-2.0
Model Index
- Name: XLSR Wav2Vec2 Lithuanina by Deividas Mataciunas
- Results:
- Task:
- Name: Speech Recognition
- Type: automatic-speech-recognition
- Dataset:
- Name: Common Voice lt
- Type: common_voice
- Args: lt
- Metrics:
- Name: Test WER
- Type: wer
- Value: 56.55
đ Quick Start
When using this model, make sure that your speech input is sampled at 16kHz.
⨠Features
- Fine - tuned on the Lithuanian language using the Common Voice dataset.
- Can be used for automatic speech recognition tasks without a language model.
đĻ Installation
No specific installation steps are provided in the original document, so this section is skipped.
đģ Usage Examples
Basic Usage
import torch
import torchaudio
from datasets import load_dataset
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
test_dataset = load_dataset("common_voice", "lt", split="test[:2%]")
processor = Wav2Vec2Processor.from_pretrained("DeividasM/wav2vec2-large-xlsr-53-lithuanian")
model = Wav2Vec2ForCTC.from_pretrained("DeividasM/wav2vec2-large-xlsr-53-lithuanian")
resampler = torchaudio.transforms.Resample(48_000, 16_000)
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])
Advanced Usage
import torch
import torchaudio
from datasets import load_dataset, load_metric
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
import re
test_dataset = load_dataset("common_voice", "lt", split="test")
wer = load_metric("wer")
processor = Wav2Vec2Processor.from_pretrained("DeividasM/wav2vec2-large-xlsr-53-lithuanian")
model = Wav2Vec2ForCTC.from_pretrained("DeividasM/wav2vec2-large-xlsr-53-lithuanian")
model.to("cuda")
chars_to_ignore_regex = '[\\\\,\\\\?\\\\.\\\\!\\\\-\\\\;\\\\:\\\\"\\\\â]'
resampler = torchaudio.transforms.Resample(48_000, 16_000)
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)
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: 56.55 %
đ Documentation
The Common Voice train
, validation
datasets were used for training.
đ License
This model is licensed under the apache - 2.0 license.