Indic DiarBench

A multilingual joint diarization and ASR benchmark for Indian languages, spanning all 22 scheduled languages of India with approximately 108 hours of natural multi-speaker audio.

Dataset Summary

Indic DiarBench is a conversational speech benchmark designed to evaluate speaker-attributed ASR in realistic multi-speaker settings for Indian languages. All annotations are human-corrected with time-aligned, speaker-attributed transcriptions. The dataset captures conversational nuances prevalent in Indian speech, such as English code-mixing, dialectal variation, and frequent speaker overlap.

Recording Conditions

The corpus includes three acoustic conditions designed to capture diverse real-world scenarios:

Per-Language Statistics

Durations are in hours. NF = near-field, FF = far-field, ITW = in-the-wild.

Annotation Pipeline

All recordings are annotated using a unified human-in-the-loop pipeline:

1. Bootstrap Transcription — Initial transcripts generated using multiple independent ASR systems, presented to annotators as editable drafts.
2. Human Transcription & Speaker Attribution — Professional annotators produce time-aligned, speaker-attributed transcriptions. No machine-generated annotation is retained without human validation.
3. Code-Mixed Transcription — Annotators produce two transcription formats: native-script (all text in Indic script) and normalized (English words in Roman script, numerals in Arabic digits).
4. Quality Control — Dedicated quality checkers (2–3 per language) verify transcription consistency, code-mixing conventions, speaker timestamps, and labels. Overlapping speech segments require multiple review rounds.
5. Expert Review — In-house language-specific experts perform final quality checks.

Dataset Fields

Usage

from datasets import load_dataset

# Load a specific language
ds = load_dataset("sarvam/indic-diarbench", "Hindi", split="test")
sample = ds[0]

print(f"Language: {sample['language']}")
print(f"Duration: {sample['duration_seconds']:.1f}s")
print(f"Speakers: {sample['num_speakers']}")
print(f"Condition: {sample['dataset_type']}")

# Access speaker-attributed transcript
for seg in sample['annotated_transcript'][:5]:
    print(f"  [{seg['start_time']:.1f}-{seg['end_time']:.1f}] {seg['speaker_id']}: {seg['transcript']}")

Baseline Results

Duration-weighted aggregate metrics across all three acoustic conditions:

Citation

@inproceedings{mehendale2026indicdiarbench,
  title={Indic DiarBench: A Multilingual Joint Diarization and ASR Benchmark for Indian Languages},
  author={Mehendale, Deovrat and Mehndiratta, Aditya and Rathi, Dhruv and Bhogale, Kaushal and Khapra, Mitesh M.},
  year={2026}
}

License

This dataset is released under the CC BY 4.0 license.