GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
ramput-labs
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
ramput-labs
Model Tree
the-cramer-project/AkylAI-STT-small
Input Modalities
Output Modalities
Supported Functionality
python
import soundfile as sffrom transformers import pipeline asr = pipeline("automatic-speech-recognition", model="ramput-labs/kyrgyz-whisper-small")audio, sr = sf.read("audio.wav", dtype="float32")print(asr({"raw": audio, "sampling_rate": sr}, generate_kwargs={"language": "kk", "task": "transcribe"})["text"])Whisper has no Kyrgyz token, so pass language="kk"; it gives the best accuracy.
This snippet handles clips up to 30 s. For longer audio, use the toolkit.
FLEURS Kyrgyz dev, 100 clips without digits: WER 16.3% / CER 4.5%. Numbers are written as words ("жети миң"), so references with digits score lower.
language="kk") and added evaluation results.Apache-2.0 (see LICENSE), inherited from AkylAI-STT-small and Whisper.
The toolkit code is MIT.