Automatic Speech Recognition
Transformers
PyTorch
Uzbek
wav2vec2
mozilla-foundation/common_voice_10_0
Generated from Trainer
AIRI_UZ
Instructions to use oyqiz/uzbek_stt_1_version with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use oyqiz/uzbek_stt_1_version with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="oyqiz/uzbek_stt_1_version")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("oyqiz/uzbek_stt_1_version") model = AutoModelForCTC.from_pretrained("oyqiz/uzbek_stt_1_version", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Oyqiz jamoasi a'zolari tomonidan qilingan STT ning eng kichik versiyasi. Bu yaxshi versiya emas faqat 15ta epoch o'qitilgan!
Foziljon To'lqinov, Shaxboz Zohidov, Abduraxim Jabborov, Yahyoxon Rahimov
Bu model facebook/wav2vec2-base va MOZILLA-FOUNDATION/COMMON_VOICE_10_0 - UZ dataseti bilan 15ta epoxta o'qitilgan. O'qitish natijalari:
- Xatolik: 0.5763
- So'z xatoligi: 0.4502
O'qitish giperparameterlari
O'qitish uchun ishlatilgan giperparameterlar:
- learning_rate: 0.0003
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- total_train_batch_size: 8
- total_eval_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 15.0
- mixed_precision_training: Native AMP
O'qitish natijalari
| Xatolik | Epox | Qadam | Tasdiq xatoligi | SXD |
|---|---|---|---|---|
| 0.4736 | 3.4 | 10000 | 0.6247 | 0.6362 |
| 0.3392 | 6.8 | 20000 | 0.7254 | 0.5605 |
| 0.2085 | 10.19 | 30000 | 0.5465 | 0.5097 |
| 0.1387 | 13.59 | 40000 | 0.5984 | 0.4632 |
- Downloads last month
- 6