Instructions to use openlimi/Tunar-stt-tiny with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use openlimi/Tunar-stt-tiny with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="openlimi/Tunar-stt-tiny")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("openlimi/Tunar-stt-tiny") model = AutoModelForSpeechSeq2Seq.from_pretrained("openlimi/Tunar-stt-tiny", device_map="auto") - Notebooks
- Google Colab
- Kaggle
|
Download README.md from openlimi/Tunar-stt-tiny: direct link, hf CLI and curl.
- Browser
- Download file 1.14 kB
-
https://huggingface.co/openlimi/Tunar-stt-tiny/resolve/main/README.md
- Command line
-
hf download hf://openlimi/Tunar-stt-tiny/README.md
-
curl -L -o README.md https://huggingface.co/openlimi/Tunar-stt-tiny/resolve/main/README.md
1.14 kB
metadata
language:
- uz
library_name: transformers
base_model: moonshine-ai/moonshine-tiny
tags:
- automatic-speech-recognition
- moonshine
- uzbek
pipeline_tag: automatic-speech-recognition
Tunar-stt-tiny
Uzbek speech recognition model fine-tuned from Moonshine-tiny (v3_1500h run).
- Output alphabet: new Uzbek Latin alphabet (
ö ğ ş ç); convert witho'->ö, g'->ğ, sh->ş, ch->ç. - Custom 4096-token BPE tokenizer.
- Input: 16 kHz mono audio, up to ~30 s per segment.
Usage
import torch, soundfile as sf
from transformers import MoonshineForConditionalGeneration, AutoTokenizer, AutoFeatureExtractor
repo = "openlimi/Tunar-stt-tiny"
model = MoonshineForConditionalGeneration.from_pretrained(repo).eval()
tok = AutoTokenizer.from_pretrained(repo)
fe = AutoFeatureExtractor.from_pretrained(repo)
wav, sr = sf.read("audio.wav") # 16 kHz mono
inputs = fe(wav, sampling_rate=16000, return_tensors="pt", return_attention_mask=True)
with torch.no_grad():
ids = model.generate(**inputs, max_new_tokens=int(len(wav) / 16000 * 12) + 8)
print(tok.batch_decode(ids, skip_special_tokens=True)[0])