Tamil ASR (Qwen3-ASR) — தமிழ் பேச்சு-to-எழுத்து
State-of-the-art Tamil Automatic Speech Recognition. An LLM-based speech-to-text model fine-tuned from Qwen/Qwen3-ASR-1.7B for the Tamil language (தமிழ்). On the public FLEURS-Tamil benchmark it outperforms AI4Bharat's IndicConformer (the prior Indic SOTA) on both WER and CER, and beats OpenAI's Whisper-large-v3 by a wide margin.
Keywords: Tamil ASR · Tamil speech to text · Tamil STT · தமிழ் speech recognition · Indic ASR · Dravidian ASR
Results — FLEURS-Tamil test set (586 utterances)
| Model | WER ↓ | CER ↓ |
|---|---|---|
| Tamil-ASR-Qwen3 (this model) | 25.27% | 7.95% |
| IndicConformer-600M (AI4Bharat, prior SOTA) | 25.49% | 9.33% |
| Whisper-large-v3 (OpenAI) | 48.58% | 13.75% |
| Qwen3-ASR-1.7B (base, no Tamil support) | 153.29% | 113.24% |
- #1 on FLEURS-Tamil — beats IndicConformer on both WER (25.27 vs 25.49) and CER (7.95 vs 9.33).
- Yes — ~23 WER points better than Whisper-large-v3.
- Yes — An LLM-based ASR beating a purpose-built Conformer (CTC/RNNT) SOTA — with far less Tamil audio.
- All numbers use an identical text normalizer across every model, computed by us on the same 586 held-out clips (see Evaluation).
Model description
- Task: Automatic Speech Recognition (speech → Tamil text)
- Language: Tamil (
ta) only - Architecture: Qwen3-ASR — audio encoder + Qwen3 LLM decoder (generative ASR), 1.7B parameters
- Base model:
Qwen/Qwen3-ASR-1.7B - Audio input: 16 kHz mono
- Decoding: beam search (
num_beams=5) recommended
Training data (~1,475 hours of Tamil)
| Source | Hours | Style |
|---|---|---|
| IndicVoices (AI4Bharat) | 803 | natural / conversational |
| Shrutilipi (AI4Bharat) | 462 | read / news |
| Kathbath (AI4Bharat) | 172 | read |
| FLEURS-Tamil train + Tamil TTS | ~38 | read |
Training procedure
A two-stage recipe:
- Language adaptation — fine-tune the base on the large conversational corpus (IndicVoices) to teach Tamil; merge into the base weights.
- Read-speech domain adaptation — LoRA (rank 64, α 128) on the combined read corpora (Shrutilipi + Kathbath + FLEURS-train + TTS), 2 epochs, lr 5e-5, bf16, then merged.
Trained with ms-swift on 4× NVIDIA H100. (Note: a full-parameter fine-tune was also tried and underperformed LoRA — LoRA r64 is the released configuration.)
Evaluation
- Benchmark:
google/fleurs, configta_in,testsplit — 586 clips, fully held out (never seen in training; training corpora are separate from FLEURS-test, so there is no leakage). - Metrics: WER and CER via
jiwer. - Fairness: the same punctuation-stripping / whitespace normalizer is applied to every model (this model, IndicConformer, Whisper, base) on the same clips. Decoding: beam search (num_beams=5).
How to use
With ms-swift:
pip install ms-swift transformers==4.57.6 qwen-asr soundfile
swift infer \
--model lemuralabs/tamil-asr-qwen3 \
--val_dataset your_data.jsonl \
--infer_backend pt --max_new_tokens 256 --num_beams 5
Dataset JSONL format (one line per clip):
{"messages": [{"role": "user", "content": "<audio>"}, {"role": "assistant", "content": ""}], "audios": ["/path/to/clip.wav"]}
Audio should be 16 kHz mono.
Yes — Intended uses & limitations
Intended: transcribing Tamil speech (read and conversational), Tamil voice interfaces, captioning, transcription pipelines.
Limitations:
- Tamil only — not trained for other languages.
- Benchmarked on read speech (FLEURS); very noisy/far-field/heavy-code-mixed audio may degrade.
- May reflect biases (domain, dialect, speaker) present in the training corpora.
Acknowledgements
- Base model: Qwen/Qwen3-ASR-1.7B (Alibaba Qwen team)
- Training data: AI4Bharat (IndicVoices, Shrutilipi, Kathbath) and Google FLEURS
- Reference/comparison: AI4Bharat IndicConformer, OpenAI Whisper-large-v3
License
Apache-2.0 (inherits the base model's license). Please also respect the licenses of the training datasets.
Citation
@misc{tamil_asr_qwen3_2026,
title = {Tamil ASR (Qwen3-ASR): an LLM-based Tamil speech recognizer},
author = {Lemura Labs},
year = {2026},
howpublished = {\url{https://huggingface.co/lemuralabs/tamil-asr-qwen3}}
}