Whisper Hindi2Hinglish Swift ONNX

--- license: apache-2.0 base_model: Oriserve/Whisper-Hindi2Hinglish-Swift pipeline_tag: automatic-speech-recognition library_name: transformers.js language: - hi - en tags: - whisper - hinglish - onnx - code-switching --- # Whisper-Hindi2Hinglish-Swift (ONNX, q8) ONNX conversion of [Oriserve/Whisper-Hindi2Hinglish-Swift](https://huggingface.co/Oriserve/Whisper-Hindi2Hinglish-Swift) for in-browser use with [Transformers.js](https://huggingface.co/docs/transformers.js) (`dtype: 'q8'`, WASM/CPU friendly). The base model is `openai/whisper-base` (73M params) fine-tuned by [Oriserve](https://huggingface.co/Oriserve) on ~550 hours of noisy Indian-accented Hindi. It transcribes Hindi-English code-mixed speech into **romanized Hinglish** — English words stay in Latin script. ## Conversion - Exported with `optimum-cli export onnx --task automatic-speech-recognition-with-past` - Quantized with onnxruntime dynamic quantization (QUInt8 weights, `EnableSubgraph` for the merged decoder), matching the layout Transformers.js expects for `dtype: 'q8'`: - `onnx/encoder_model_quantized.onnx` (23 MB) - `onnx/decoder_model_merged_quantized.onnx` (79 MB) ## Usage (Transformers.js) ```js import { pipeline } from '@huggingface/transformers'; const asr = await pipeline( 'automatic-speech-recognition', 'TechHirecentive/Whisper-Hindi2Hinglish-Swift-ONNX', { dtype: 'q8' }, ); const { text } = await asr(audioFloat32Array16kHz, { language: 'hi', task: 'transcribe', }); ``` ## License Apache-2.0, same as the upstream fine-tune. All credit for the model weights to [Oriserve](https://huggingface.co/Oriserve); this repo only repackages them as quantized ONNX.

Source context: 608 downloads · 0 likes · Pipeline automatic-speech-recognition · Library transformers.js · Repo Hirecentive-D3l/Whisper-Hindi2Hinglish-Swift-ONNX