GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
kaan84
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
kaan84
Model Tree
openai/whisper-small
Input Modalities
Output Modalities
Supported Functionality
| Item | Value |
|---|---|
| Task | Automatic speech recognition |
| Language | Sinhala (si) |
| Base model | openai/whisper-small |
| Architecture | Whisper / AutoModelForSpeechSeq2Seq |
| Parameters | Approximately 241.7M |
| Framework | Transformers |
| Status | Experimental prototype |
Use this checkpoint for research, baseline comparison, testing, and further fine-tuning. It should not be treated as a validated production model until dataset documentation and held-out evaluation results are added.
python
import torchfrom transformers import pipeline model_id = "kaan84/whisper-small-sinhala-proto"device = 0 if torch.cuda.is_available() else -1 transcriber = pipeline( task="automatic-speech-recognition", model=model_id, device=device,) result = transcriber( "sample.wav", generate_kwargs={"language": "si", "task": "transcribe"},)print(result["text"])The model metadata identifies large-sinhala-asr-dataset as the training dataset. For reproducibility, document its repository link, source, license, total duration, speaker distribution, split strategy, audio sampling rate, transcript normalization, and quality-control process.
The checkpoint was generated using the Transformers Trainer workflow. Add the exact learning rate, batch size, gradient-accumulation steps, epoch or step count, warm-up schedule, precision, hardware, seed, and checkpoint-selection rule.
No validated evaluation results are declared in the current repository metadata.
| Metric | Validation | Test |
|---|---|---|
| Word Error Rate (WER) | To be added | To be added |
| Character Error Rate (CER) | To be added | To be added |
Apache License 2.0. Users must also comply with the licenses and terms of the base model and training data.
This repository should remain clearly labeled as a prototype. If kaan84/whisper-small-sinhala-v1 is the selected release model, direct general users to that repository and retain this checkpoint for comparison and reproducibility.
import torchfrom transformers import pipeline model_id = "kaan84/whisper-small-sinhala-proto"device = 0 if torch.cuda.is_available() else -1 transcriber = pipeline( task="automatic-speech-recognition", model=model_id, device=device,) result = transcriber( "sample.wav", generate_kwargs={"language": "si", "task": "transcribe"},)print(result["text"])