GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. 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 |
| Parameters | Approximately 241.7M |
| Weight format | Safetensors |
The model is suitable for research, prototyping, and Sinhala speech-transcription experiments. Potential applications include transcription tools, subtitle preparation, voice interfaces, and accessibility workflows.
Performance can vary with accent, background noise, recording quality, speaking rate, and domain-specific vocabulary. Review generated transcripts before using them in high-impact workflows.
python
import torchfrom transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipelinemodel_id = "kaan84/whisper-small-sinhala-v1"device = "cuda:0" if torch.cuda.is_available() else "cpu"torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32model = AutoModelForSpeechSeq2Seq.from_pretrained(model_id,torch_dtype=torch_dtype,low_cpu_mem_usage=True,use_safetensors=True,)model.to(device)processor = AutoProcessor.from_pretrained(model_id)asr = pipeline("automatic-speech-recognition",model=model,tokenizer=processor.tokenizer,feature_extractor=processor.feature_extractor,torch_dtype=torch_dtype,device=device,)result = asr("sample.wav", generate_kwargs={"language": "si", "task": "transcribe"})print(result["text"])
The repository metadata does not currently provide a complete dataset card. Add the following before treating this model as production-ready documentation:
This model was fine-tuned from openai/whisper-small. Training hyperparameters, hardware, checkpoint-selection criteria, and preprocessing settings should be added here to make the result reproducible.
Add evaluation results on a held-out Sinhala test set.
| Metric | Result |
|---|---|
| Word Error Rate (WER) | To be added |
| Character Error Rate (CER) | To be added |
Apache License 2.0. Confirm that all training datasets and redistributed assets are compatible with this license.
If you use this model, cite the original Whisper paper and link to this model repository. Add a project-specific BibTeX entry when the training work is formally published.