| --- |
| license: apache-2.0 |
| language: [hi, ta, te, bn, mr, pa, gu, kn, ml] |
| tags: [automatic-speech-recognition, onnx, indicconformer, quantized] |
| --- |
| |
| # IndicConformer per-language ONNX packs (int8, external data) |
|
|
| Nine per-language speech-recognition packs for the Indian languages, prepared for |
| on-device use: **131 MB each**, against 622 MB for the 22-language multilingual |
| model they replace. |
|
|
| Derived from [AI4Bharat IndicConformer](https://huggingface.co/ai4bharat) via the |
| ONNX exports published by |
| [OpenVoiceOS](https://huggingface.co/OpenVoiceOS). Two changes were applied to |
| each, both necessary to run on ONNX Runtime's CPU provider on a phone: |
|
|
| 1. **Re-quantized from QInt8 to QUInt8.** The upstream `model.int8.onnx` fails to |
| create a session with `Could not find an implementation for ConvInteger(10)`: |
| ORT's CPU `ConvInteger` kernel is uint8-only, and a Conformer's pre-encode is |
| convolutional. The fp32 model was quantized here instead. |
| 2. **Initializers moved to an external file.** The single-file build copies its |
| weights into the arena — 202 MiB resident on an iPhone. As mapped external |
| data that is ~30 MiB, because the pages stay clean and file-backed. |
|
|
| Each pack is `model.int8.opt.onnx` (graph) + `model.int8.opt.onnx.data` (weights) |
| + `vocab.txt`, plus the filterbank and window the featurizer needs |
| (`mel_filters.json`, `hanning_window.json`), which the upstream exports do not |
| include. |
|
|
| ## Shape |
|
|
| Single fused graph — the CTC output is already the language's own vocabulary, so |
| no column masking is needed: |
|
|
| ``` |
| audio_signal [batch, 80, frames] + length [batch] -> logprobs [batch, frames, vocab] |
| ``` |
|
|
| 80 log-mel filters at 16 kHz, subsampling factor 4. `<blk>` is the last vocabulary |
| entry. |
|
|
| ## Accuracy |
|
|
| Measured on one held-out clip per language (61 words total): **80.3% exact word |
| match**, against 86.9% for the 22-language model on the same clips. Smaller and |
| several times faster, for a few points of accuracy. |
|
|
| | te | bn | pa | gu | kn | hi | mr | ml | ta | |
| |---|---|---|---|---|---|---|---|---| |
| | 6/6 | 6/6 | 7/9 | 6/7 | 5/6 | 5/7 | 5/7 | 5/7 | 4/6 | |
|
|
