yi-whisper-large-v3 — ONNX
ONNX build of ivrit-ai/yi-whisper-large-v3 for running Yiddish speech
recognition in the browser with transformers.js.
No weights were retrained. This is a format conversion plus quantisation, so that the model can be downloaded once by a web page and run locally on the user's own machine — audio never leaves the device.
Variants: q4, q4f16.
Attribution
The underlying model is a Yiddish finetune of openai/whisper-large-v3 trained by
ivrit-ai and released under Apache-2.0. All credit for
the Yiddish capability belongs to them; this repository only changes the file format.
Note on the translate task
Per the upstream model card, the translation task was not trained and is degraded.
Use task: "transcribe" with language: "yi", and translate the resulting text
separately.
- Downloads last month
- 20