Wav2vec2 Large Xlsr Turkish Artificial

🚀 Wav2Vec2-Large-XLSR-Turkish

This is a fine - tuned facebook/wav2vec2-large-xlsr-53 model on the Turkish Artificial Common Voice dataset, which can be used for automatic speech recognition.

🚀 Quick Start

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

✨ Features

• Language: Turkish
• Datasets: Common Voice
• Metrics: Word Error Rate (WER)
• Tags: audio, automatic - speech - recognition, speech, xlsr - fine - tuning - week
• License: Apache 2.0

📦 Installation

No specific installation steps are provided in the original README. However, you need to have the necessary Python libraries installed, such as torch, torchaudio, datasets, and transformers. You can install them using pip:

pip install torch torchaudio datasets transformers

💻 Usage Examples

Basic Usage

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

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

processor = Wav2Vec2Processor.from_pretrained("cahya/wav2vec2-large-xlsr-turkish-artificial")
model = Wav2Vec2ForCTC.from_pretrained("cahya/wav2vec2-large-xlsr-turkish-artificial")


# 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"])
  resampler = torchaudio.transforms.Resample(sampling_rate, 16_000)
  batch["speech"] = resampler(speech_array).squeeze().numpy()
  return batch

test_dataset = test_dataset.map(speech_file_to_array_fn)
inputs = processor(test_dataset[:2]["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)

print("Prediction:", processor.batch_decode(predicted_ids))
print("Reference:", test_dataset[:2]["sentence"])

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", "tr", split="test")
wer = load_metric("wer")

processor = Wav2Vec2Processor.from_pretrained("cahya/wav2vec2-large-xlsr-turkish-artificial")
model = Wav2Vec2ForCTC.from_pretrained("cahya/wav2vec2-large-xlsr-turkish-artificial") 
model.to("cuda")

chars_to_ignore_regex = '[\,\?\.\!\-\;\:\"\“\‘\”\'\`…\’»«]'

# 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"])
  resampler = torchaudio.transforms.Resample(sampling_rate, 16_000)
  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: 66.98 %

📚 Documentation

The model can be evaluated on the Turkish test data of Common Voice as shown in the advanced usage example.

The Artificial Common Voice train, validation is used to fine - tune the model. The script used for training can be found here

📄 License

This project is licensed under the Apache 2.0 license.