Modelpublic

OpenVoiceOS/misterkissi-whisper-small-vai-onnx

sourceHugging Facecc-by-nc-sa-4.0updated 2mo agoView on Hugging Face

0likes56downloads

Model Card

misterkissi-whisper-small-vai-onnx (ONNX)

ONNX export of misterkissi/whisper-small-vai, a Vai whisper-small ASR model fine-tuned by Emmanuel Kissi on top of openai/whisper-small, for use with onnx-asr and the OVOS onnx-asr STT plugin.

Usage

import onnx_asr

model = onnx_asr.load_model("OpenVoiceOS/misterkissi-whisper-small-vai-onnx")
print(model.recognize("test.wav"))

Or with the OVOS plugin:

from ovos_stt_plugin_onnx_asr import OnnxASRSTT

stt = OnnxASRSTT(config={"model": "OpenVoiceOS/misterkissi-whisper-small-vai-onnx"})

Export

bash

$ export FORCE_ONNX_EXTERNAL_DATA=1
$ optimum-cli export onnx --task automatic-speech-recognition-with-past --model misterkissi/whisper-small-vai whisper-onnx
$ cd whisper-onnx && rm decoder.onnx* decoder_with_past_model.onnx*  # only the merged decoder is needed

License

CC BY-NC-SA 4.0, inherited from the source model misterkissi/whisper-small-vai.