ipsilondev/lite-whisper-large-v3-turbo-timestamped-onnx
By ipsilondev · ↓ 2 · ♥ 0 · Updated 2026-01-01
What's in this repo
This page lists the files in ipsilondev/lite-whisper-large-v3-turbo-timestamped-onnx, including decoder_model_merged.onnx, decoder_model_merged_int8.onnx, decoder_model_merged_quantized.onnx and more.
- 5 ONNX models (.onnx files)
- 17 files, including 9 .json, 5 .onnx, 1 .md, 1 .txt
- Last updated 2026-01-01
ONNX files
| File | Size | Download |
|---|---|---|
| onnx/decoder_model_merged.onnx | — | Download |
| onnx/decoder_model_merged_int8.onnx | — | Download |
| onnx/decoder_model_merged_quantized.onnx | — | Download |
| onnx/encoder_model.onnx | — | Download |
| onnx/encoder_model_fp16.onnx | — | Download |
How to use
These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.
README
LiteWhisper Large V3 Turbo ONNX
Word-level timestamps via cross-attention.
Models
| Encoder | Decoder | Size |
|---|---|---|
| FP32 | FP32 | 2.1 GB |
| FP16 | quantized | 1.2 GB (recommended) |
Usage
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" });Model info
automatic-speech-recognition
transformers.js
transformers.js
onnx
whisper
automatic-speech-recognition
speech-recognition
license:mit
region:us
↓ 2
♥ 0
Created: 2026-01-01
Updated: 2026-01-01
View on Hugging FaceFiles (17)
.gitattributes
README.md
added_tokens.json
config.json
generation_config.json
merges.txt
normalizer.json
onnx/decoder_model_merged.onnx
ONNX
onnx/decoder_model_merged_int8.onnx
ONNX
onnx/encoder_model.onnx
ONNX
onnx/encoder_model_fp16.onnx
ONNX
preprocessor_config.json
special_tokens_map.json
tokenizer.json
tokenizer_config.json
vocab.json