GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
aahanlulla18
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
aahanlulla18
Model Tree
openai/whisper-medium
Input Modalities
Output Modalities
Supported Functionality
Sindhi is one of the most under-resourced languages in Whisper's training data. In testing,
stock whisper-medium almost never produces a correct Sindhi transcription — it frequently
understands the sounds of Sindhi speech correctly, but writes the output in the wrong
script entirely (Devanagari or Romanized text instead of Sindhi's actual script), or
collapses into repeating meaningless characters.
This project quantified that failure and tested whether lightweight fine-tuning (LoRA) on a small amount of real Sindhi speech could correct it.
Evaluated on a held-out set of 324 human-validated Sindhi clips from Mozilla Common Voice 26.0, fine-tuned on 200 separate training clips using LoRA (~1.2% of the model's parameters trained):
| Metric | Before fine-tuning | After fine-tuning |
|---|---|---|
| Word Error Rate (WER) | 148.35% | 72.97% |
| Exact word matches | 7 | 819 |
| Insertions (garbled/looping output) | 1,250 | 124 |
| Substitutions | 1,791 | 1,624 |
| Deletions | 773 | 128 |
Key finding: fine-tuning almost entirely fixed the wrong-script and gibberish-loop failure modes (insertions dropped ~90%), and the model now consistently outputs real Sindhi script. Word-level accuracy (substitutions) improved more modestly — with only 200 training clips, the model learned what Sindhi script looks like far better than it learned precise vocabulary. This is an honest, expected limitation of fine-tuning on a small dataset, not a fully "solved" result.
openai/whisper-mediumResearch and experimentation with Sindhi ASR. Not intended for production or safety-critical transcription use without further evaluation.