GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
awaaz-se-alfaaz
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
awaaz-se-alfaaz
Model Tree
openai/whisper-large-v3-turbo
Input Modalities
Output Modalities
Supported Functionality
python
!pip install -U "torchao>=0.16.0" peftfrom transformers import WhisperProcessor, WhisperForConditionalGenerationfrom peft import PeftModelbase = WhisperForConditionalGeneration.from_pretrained("openai/whisper-large-v3-turbo")model = PeftModel.from_pretrained(base, "awaaz-se-alfaaz/whisper-turbo-v3-urdu")processor = WhisperProcessor.from_pretrained("awaaz-se-alfaaz/whisper-turbo-v3-urdu")
Benchmark WER (%) — LoRA fine-tuning
| Dataset | Whisper-Turbo (Zero-Shot) | Whisper-Turbo (Fine-Tuned) | Relative Reduction |
|---|---|---|---|
| CSaLT | 27.51 | 20.77 | 24.5% |
| Common Voice v23 | 37.23 | 25.78 | 30.8% |
| FLEURS | 24.07 | 16.86 | 29.9% |
YouTube Evaluation Set (real-world, multi-speaker)
| Model | WER (%) |
|---|---|
| Whisper-Turbo | 25.33 |
| Whisper-Turbo Fine-Tuned | 24.20 |
SLM Post-Processing on YouTube Set
| SLM Corrector | Whisper-Turbo | Whisper-Turbo Fine-Tuned |
|---|---|---|
| Gemma3-12B (4-bit) | 21.93 | 21.75 |
| Qwen3-14B (4-bit) | 23.58 | 22.39 |
| Tiny-Aya-Fire | 28.81 | 24.64 |
| Qwen3-4B | 30.57 | 29.41 |
[BibTeX once camera-ready is finalized]