OmoN-STT

Uzbek speech recognition model trained from islomov/rubaistt_v2_medium.

Dataset size: ~244k audio samples
Training time: ~190 hours
Epochs: 3

Training

Base model: islomov/rubaistt_v2_medium

Training setup:

GPU: RTX 3080 Ti

Batch size: 8

Gradient accumulation: 4

Epochs: 3

Total training steps: 22251

Usage

import torch
import librosa
from transformers import WhisperProcessor, WhisperForConditionalGeneration

processor = WhisperProcessor.from_pretrained("omullaboyev/OmoN-STT")
model = WhisperForConditionalGeneration.from_pretrained("omullaboyev/OmoN-STT")

audio, sr = librosa.load("audio.wav", sr=16000)

inputs = processor(audio, sampling_rate=16000, return_tensors="pt")

with torch.no_grad():
    predicted_ids = model.generate(inputs["input_features"])

text = processor.batch_decode(predicted_ids, skip_special_tokens=True)

print(text)