Downloads · 30 days
20
9% of all-time downloads
uzbek-stt-fastconformer-v1.2
zafarrr/uzbek-stt-fastconformer-v1.2
uzbek-stt-fastconformer-v1.2 is a automatic speech recognition model from zafarrr. Use it when you need speech turned into text. It is set up for nemo. The card lists the license as apache-2.0.
114M parametrli FastConformer Hybrid RNNT-CTC modeli. O'zbek tilida nutqni matnga aylantiradi.
All-time downloads
215
Public
Repo size
459 MB
Likes
4
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
- Feb 27, 2026
- Updated
- Feb 27, 2026
- SHA
- 627e8e16
Model card
From the Hugging Face model README
O'zbek nutqni aniqlash modeli (ASR) — FastConformer v1.2
114M parametrli FastConformer Hybrid RNNT-CTC modeli. O'zbek tilida nutqni matnga aylantiradi.
Natijalar
| Metrika | Qiymat |
|---|---|
| WER | 8.31% |
| Trening ma'lumot | 104 soat |
| Parametrlar | 114M |
Ishlatish
import nemo.collections.asr as nemo_asr
model = nemo_asr.models.EncDecHybridRNNTCTCBPEModel.restore_from("uzbek_stt_v12.nemo")
model.eval()
natija = model.transcribe(["audio.wav"])
print(natija[0])
Kod
- Task
- Automatic Speech Recognition
- Library
- nemo
- License
- apache-2.0
- Languages
- uz
- Created
- Feb 27, 2026
- Updated
- Feb 27, 2026