Open-weight model
whisper-hinglish-tiny-onnx
by Gaurav Mahajan mahajanGaurav/whisper-hinglish-tiny-onnx
whisper-hinglish-tiny-onnx is an open-weight model from Gaurav Mahajan. Its published files total 104.6 MB.
Hindi audio in → Roman-script Hinglish captions out. 100% in-browser, no server. This is a browser-fixed repack of (fine-tune of openai/whisper-tiny for Hindi → Hinglish).
Model Card
Hindi audio in → Roman-script Hinglish captions out. 100% in-browser, no server. This is a browser-fixed repack of (fine-tune of openai/whisper-tiny for Hindi → Hinglish). Original model and training credit belong to the original author — this repo only fixes the two browser blockers and trims the package for web use. Young India reads Hindi in Roman script (WhatsApp/Instagram culture) — they speak Hindi but don't read Devanagari. This model outputs captions the ~102 MB total — small enough to run on-device via transformers.js, including mobile browsers. 1. tokenizer.json — BPE merges were stored as lists (["a", "b"]); converted to strings ("a b"), which is what the browser tokenizer path…
Excerpt from the card by Gaurav Mahajan.
Configuration
- Architecture
- WhisperForConditionalGeneration
- Layers
- 6
- Vocabulary size
- 51,865
- Model type
- whisper
Identity and Version
- Repository
- mahajanGaurav/whisper-hinglish-tiny-onnx
- Publisher
- Gaurav Mahajan
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- Not stated by the source
- Languages
- Not stated by the source
- Revision
- 62a7ce4bd9929bac2ac6df28ecfb727b94488525
- First published
- 2026-10-15
- Last updated
- 2026-10-16
Files and Weights
9 files, 104.6 MB in total. The weights are 2 files totalling 102.5 MB in onnx.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| onnx/decoder_model_merged_quantized.onnx | Weights | 79.3 MB | ffab3719c07a |
| onnx/encoder_model_quantized.onnx | Weights | 23.1 MB | 0cd4fb050fa9 |
| config.json | Configuration | 2.2 KB | — |
| generation_config.json | Configuration | 3.6 KB | — |
| preprocessor_config.json | Configuration | 356 B | — |
| README.md | Documentation | 2.2 KB | — |
| .gitattributes | Repository | 1.5 KB | — |
| tokenizer.json | Tokenizer | 1.8 MB | — |
| tokenizer_config.json | Tokenizer | 282.6 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 102.5 MB
Released by Gaurav Mahajan through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 102.5 MB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.