Azerbaijani ASR Dataset

Dataset Description

This dataset contains Azerbaijani speech data for Automatic Speech Recognition (ASR) tasks.

Dataset Summary

• Language: Azerbaijani (az)
• Task: Automatic Speech Recognition
• Total Duration: ~328 hours
• Total Samples: ~345,643 audio-text pairs
• Audio Format: WAV, 16kHz sampling rate
• License: CC-BY-4.0

Dataset Structure

Each audio segment is specially numbered so that you can merge them if you need to create longer segments.

DatasetDict({
    train: Dataset({
        features: ['audio', 'text', 'duration', 'audio_file'],
        num_rows: [total_samples]
    })
})

Features

• audio: Audio file (WAV format, 16kHz)
• text: Transcription of the audio (Azerbaijani text)
• duration: Duration of audio clip in seconds
• audio_file: Original filename of the audio segment

Usage

from datasets import load_dataset

# Load the dataset
dataset = load_dataset("LocalDoc/azerbaijani_asr")

# Access train split
train_dataset = dataset["train"]

# Example usage
for example in train_dataset:
    audio = example["audio"]
    text = example["text"]
    duration = example["duration"]

Duration Distribution

• 0-2 sec: 36.1%
• 2-5 sec: 47.2%
• 5-10 sec: 14.6%
• 10-20 sec: 2.0%
• 20+ sec: 0.1%

Use Cases

• Fine-tuning Whisper models for Azerbaijani
• Training new ASR models for Azerbaijani language
• Benchmarking ASR performance on Azerbaijani

Citation

If you use this dataset, please cite:

@dataset{azerbaijani_asr_2025,
  title={Azerbaijani ASR Dataset},
  author={LocalDoc},
  year={2025},
  url={https://huggingface.co/datasets/LocalDoc/azerbaijani_asr}
}