Downloads · 30 days
109
14% of all-time downloads
asr-uz-fastconformer-large
uzinfocom-edu-ai/asr-uz-fastconformer-large
asr-uz-fastconformer-large is a automatic speech recognition model from uzinfocom-edu-ai. Use it when you need speech turned into text. It is set up for nemo. The card lists the license as apache-2.0.
Fine-tuned NVIDIA FastConformer Hybrid Transducer+CTC model for Uzbek automatic speech recognition.
All-time downloads
765
Public
Repo size
459 MB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.nemo459 MB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- nemo
- License
- apache-2.0
- Access
- Public
- Created
- Jun 26, 2026
- Updated
- Jun 26, 2026
- SHA
- 9d9500ca
Base models
Model card
From the Hugging Face model README
Uzbek FastConformer Hybrid RNNT+CTC (Large)
Fine-tuned NVIDIA FastConformer Hybrid Transducer+CTC model for Uzbek automatic speech recognition.
Model Details
| Base model | nvidia/stt_uz_fastconformer_hybrid_large_pc |
| Architecture | EncDecHybridRNNTCTCBPEModel (FastConformer encoder + RNNT/CTC decoders) |
| Training data | uzinfocom-edu-ai/uzbek-asr-curated-701h (~701 hours, 6 sources) |
| Parameters | ~120M |
| Format | NeMo .nemo |
| Precision | fp32 |
Performance
| Metric | Value |
|---|---|
| WER (RNNT) | 16.01% |
| CER | 6.12% |
| Test set size | 27,142 utterances |
WER by Source
| Source | WER |
|---|---|
| uzbekvoice (read speech) | 6.85% |
| news_youtube | 28.61% |
| it_youtube | 32.10% |
| podcasts_dialect | 44.51% |
Usage
import nemo.collections.asr as nemo_asr
model = nemo_asr.models.EncDecHybridRNNTCTCBPEModel.from_pretrained(
"uzinfocom-edu-ai/asr-uz-fastconformer-large"
)
model.eval()
transcriptions = model.transcribe(["audio.wav"], batch_size=1)
print(transcriptions[0].text)
Training Configuration
- GPUs: 3× NVIDIA Tesla V100
- Batch size: 8 × 3 GPUs × 8 gradient accumulation = 192 effective
- Learning rate: 5e-5 (AdamW, cosine annealing, 5% warmup)
- Epochs: 40 (best checkpoint at epoch 31)
- Encoder freeze: first 3 epochs
- Strategy: DDP (NCCL)
Data Sources
The model was trained on a curated multi-source Uzbek speech corpus (~701 hours):
| Source | Hours | Domain |
|---|---|---|
| Common Voice (uz) | 157.9h | Crowdsourced read speech |
| UzbekVoice | 125.0h | Book/read speech (capped) |
| News YouTube | 137.6h | Broadcast news |
| IT YouTube | 134.8h | Tech content |
| Podcasts (Tashkent dialect) | 94.8h | Conversational |
| Uzbek Speech Corpus (ISSAI) | 50.5h | Studio recordings |
Developed by
uzinfocom-edu-ai
- Task
- Automatic Speech Recognition
- Library
- nemo
- License
- apache-2.0
- Languages
- uz
- Created
- Jun 26, 2026
- Updated
- Jun 26, 2026