Downloads · 30 days
6
10% of all-time downloads
ipsilondev/lite-whisper-large-v3-turbo-timestamped-onnx
lite-whisper-large-v3-turbo-timestamped-onnx is a automatic speech recognition model from ipsilondev. Use it when you need speech turned into text. It is set up for transformers.js. The card lists the license as mit.
Word-level timestamps via cross-attention.
Downloads · 30 days
6
10% of all-time downloads
All-time downloads
63
Public
Repo size
3.4 GB
Likes
0
Public
Click a slice to open those files.
.onnx3.9 GB · 100%
From the Hugging Face model README
Word-level timestamps via cross-attention.
| Encoder | Decoder | Size |
|---|---|---|
| FP32 | FP32 | 2.1 GB |
| FP16 | quantized | 1.2 GB (recommended) |
const transcriber = await pipeline(
"automatic-speech-recognition",
"ipsilondev/lite-whisper-large-v3-turbo-onnx",
{ dtype: { encoder_model: "fp16", decoder_model_merged: "quantized" } }
);
const result = await transcriber(audio, { return_timestamps: "word" });