Downloads · 30 days
26
18% of all-time downloads
whisper-small-manglish
jona276/whisper-small-manglish
whisper-small-manglish is a automatic speech recognition model from jona276. Use it when you need speech turned into text. The card lists the license as apache-2.0.
Fine-tuned Whisper Small model for Malayalam-English code-switched automatic speech recognition (Manglish).
All-time downloads
146
Public
Parameters
242M
967 MB on disk
Likes
2
Public
Repo makeup
Click a slice to open those files.
.safetensors967 MB · 100%
At a glance
- Task
- Automatic Speech Recognition
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Jun 16, 2026
- Updated
- Jun 16, 2026
- SHA
- 9a5c02b6
Base models
Datasets
Model card
From the Hugging Face model README
Whisper Small Manglish
Fine-tuned Whisper Small model for Malayalam-English code-switched automatic speech recognition (Manglish).
Results
| Model | WER ↓ | CER ↓ |
|---|---|---|
| Whisper Medium | 111.64% | 82.64% |
| Sarvam Saaras v3 Codemix | 48.61% | 21.95% |
| Whisper Small (Fine-Tuned) | 44.38% | 16.53% |
Training Data
Manglish ASR Benchmark
- Train: 2,098 clips
- Validation: 285 clips
- Test: 500 clips
Data Leakage Verification
- Train ∩ Test = 0
- Validation ∩ Test = 0
- Train ∩ Validation = 0
Dataset
https://huggingface.co/datasets/jona276/manglish-asr-benchmark
Usage
from transformers import pipeline
pipe = pipeline( "automatic-speech-recognition", model="jona276/whisper-small-manglish" )
result = pipe("audio.wav") print(result["text"])
Limitations
- Evaluated only on the Manglish benchmark
- Strict transcript matching
- Script-equivalent words are counted as errors
- Task
- Automatic Speech Recognition
- Type
- whisper
- License
- apache-2.0
- Languages
- ml, en
- Created
- Jun 16, 2026
- Updated
- Jun 16, 2026