POWSM encoder + CTC β€” ONNX int8

An adapted copy of espnet/powsm by Chin-Jou Li, Kalvin Chang, Shikhar Bharadwaj, Eunjung Yeo, Kwanghee Choi, Jian Zhu, David R. Mortensen and Shinji Watanabe (POWSM: A Phonetic Open Whisper-Style Speech Foundation Model). Licensed, like the original, under CC BY 4.0.

Changes made: only the encoder and the CTC head are exported (the attention decoder is dropped, so no language/task prompt is needed); the front end (STFT β†’ 80 log-mel β†’ global MVN) is left out of the graph and described in frontend.json; weights dynamically quantised to int8 with onnxruntime. Export script: speech-to-ipa/eval/export_powsm_onnx.py.

Files

  • model.int8.onnx β€” inputs feats float32 [1, T, 80] (normalised log-mel), feats_lens int64 [1]; output logits [1, frames, 40002].
  • frontend.json β€” window, mel filters and normalisation statistics.
  • vocab.json β€” {"blank": 0, "vocab": {phone: id}}, phone tokens only (6,405 of 40,002). Greedy CTC: argmax per frame, merge repeats, keep phone ids.

Accuracy

On 760 VoxAngeles utterances (8 from each of 95 languages), narrow scoring, no language hint: CTC-only PER 53.2 / PFER 14.7 (this int8 copy 53.9 / 15.1), vs 56.2 / 17.6 for the full model's attention decoder with <unk> language.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Model tree for ThePowerOfHebrew/powsm-ctc-onnx

Base model

espnet/powsm
Quantized
(2)
this model

Paper for ThePowerOfHebrew/powsm-ctc-onnx