Downloads · 30 days
75
34% of all-time downloads
instush/ivrit-whisper-large-v3-turbo-timestamped-onnx
ivrit-whisper-large-v3-turbo-timestamped-onnx is a automatic speech recognition model from instush. Use it when you need speech turned into text. It is set up for transformers.js. The card lists the license as apache-2.0.
Unofficial ONNX conversion of ivrit-ai/whisper-large-v3-turbo (a Hebrew fine-tune of openai/whisper-large-v3-turbo), for in-browser use with 🤗 Transformers.js.
Downloads · 30 days
75
34% of all-time downloads
All-time downloads
220
Public
Repo size
5.6 GB
Likes
0
Public
Click a slice to open those files.
.onnx3.1 GB · 55%
From the Hugging Face model README
Unofficial ONNX conversion of ivrit-ai/whisper-large-v3-turbo (a Hebrew fine-tune of openai/whisper-large-v3-turbo), for in-browser use with 🤗 Transformers.js.
What was modified relative to the source model (per Apache-2.0 §4(b)):
output_attentions=True, so the decoder graph
exposes cross_attentions.* outputs. This is what enables
word-level timestamps (return_timestamps: "word") in Transformers.js —
the same technique as the onnx-community/*_timestamped exports. The
official ivrit-ai/whisper-large-v3-turbo-onnx export does not include
these outputs and therefore supports segment-level timestamps only.fp16, q4); weights are otherwise unchanged.All credit for the model itself goes to ivrit.ai (fine-tune, ~5,050 h of Hebrew training data) and OpenAI (base model).
import { pipeline } from "@huggingface/transformers";
const transcriber = await pipeline(
"automatic-speech-recognition",
"instush/ivrit-whisper-large-v3-turbo-timestamped-onnx",
{
device: "webgpu", // large model — WebGPU strongly recommended
dtype: { encoder_model: "fp16", decoder_model_merged: "q4" },
},
);
const out = await transcriber(audioFloat32Array16kHz, {
language: "he",
task: "transcribe",
chunk_length_s: 30,
stride_length_s: 5,
return_timestamps: "word",
});
Notes:
language: "he"
explicitly (the fine-tune degraded language auto-detection).Apache License 2.0 — same as the source models. See the license text in this repo / the HF license tag. This is not an official ivrit.ai or OpenAI release.