đ Wav2Vec2-Large-XLSR-53-Tatar
This model is a fine - tuned version of facebook/wav2vec2-large-xlsr-53 on Tatar using the Common Voice dataset. Ensure your speech input is sampled at 16kHz when using this model.
đ Quick Start
This model is a fine - tuned version of facebook/wav2vec2-large-xlsr-53 on Tatar using the Common Voice dataset. When using this model, make sure that your speech input is sampled at 16kHz.
⨠Features
- Language: Tatar
- Datasets: Common Voice
- Metrics: Word Error Rate (WER)
- Tags: audio, automatic - speech - recognition, speech, xlsr - fine - tuning - week
đĻ Installation
No specific installation steps are provided in the original document.
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", "tt", split="test[:2%]")
processor = Wav2Vec2Processor.from_pretrained("crang/wav2vec2-large-xlsr-53-tatar")
model = Wav2Vec2ForCTC.from_pretrained("crang/wav2vec2-large-xlsr-53-tatar")
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", "tt", split="test")
wer = load_metric("wer")
processor = Wav2Vec2Processor.from_pretrained("crang/wav2vec2-large-xlsr-53-tatar")
model = Wav2Vec2ForCTC.from_pretrained("crang/wav2vec2-large-xlsr-53-tatar")
model.to("cuda")
chars_to_ignore_regex = '[\,\?\.\!\-\u2013\u2014\;\:\"\\%\\\]'
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
The Word Error Rate (WER) on the test data is 30.93 %.
đ Documentation
The Common Voice train
and validation
datasets were used for training.
đ License
This model is licensed under the Apache 2.0 license.
đ Model Information
Property |
Details |
Model Name |
Tatar XLSR Wav2Vec2 Large 53 |
Model Type |
Fine - tuned Wav2Vec2 - Large - XLSR - 53 on Tatar |
Training Datasets |
Common Voice (train and validation sets) |
Evaluation Metric |
Word Error Rate (WER) |
Test WER |
30.93 |