alt.freeweights.speech / whisper-medium.en_timestamped
From: onnx-community <huggingface.co/onnx-community>Newsgroups: alt.freeweights.speechSubject:

whisper-medium.en_timestamped

Date: 2026-11-15Commit: 475d02bSigned: 2DC28CC7B26A283B ✓

Automatic speech recognition model. Onnx weights, 26.2 GB in all. Published by onnx-community under MIT.

speech26.2GBwhisper-medium.en_timestampedonnxpermissive
FactsParamsnot statedSize26.2 GBFormatsonnxTaskautomatic speech recognitionLicenseMITFrom sourcepermissive
$ fw get onnx-community/whisper-medium.en_timestamped
# manifest sha256 3b56bde4ed50… · 26.2 GB · 57 files
$ fw verify ./whisper-medium.en_timestamped onnx-community/whisper-medium.en_timestamped
From sourceHosted (signed)onnx-community/whisper-medium.en_timestampedLast check: 2026-11-15 05:18 UTC

Get help: custom fine-tune or private deploy. We review your setup before we quote.

Quantized of whisper-medium.en.

Works with

Convert with

Scan with

Overview

Size
26.2 GB
Weights
181 MB (smallest of 34 ONNX variants)
Parameters
not stated
Formats
onnx
Task
automatic speech recognition
License
MIT (permissive)
Files
57, each with a sha256
Publisher
onnx-community
Added
2026-11-15
Section
alt.freeweights.speech
Lineage

Original release from the publisher.

Base model: openai/whisper-medium.en

Where these bytes come from
Publisher at the pinned commit→You

Sources are tried in order. A file counts only when its size and sha256 match the manifest. Sources are checked when you ask for them, not on a timer.

Sources
BadgeHostLast checkResult
From sourcehuggingface.co2026-11-15 05:18 UTCpassed

Model card

From the publisher at commit 475d02b. Shown as plain text with links; images open at the publisher.

whisper-medium.en_timestamped#

This is the ONNX version of openai/whisper-medium.en with word-level timestamp support for use with Transformers.js.

Features#

  • ✅ Word-level timestamps via cross-attention (alignment_heads configured)
  • ✅ Multiple quantization variants (fp32, int8, uint8)
  • ✅ Compatible with Transformers.js for browser-based inference
  • ✅ Merged decoder model for efficient inference

Usage with Transformers.js#

import { pipeline } from '@huggingface/transformers';

const transcriber = await pipeline(
  'automatic-speech-recognition',
  'neonwatty/whisper-medium.en_timestamped'
);

const result = await transcriber(audioUrl, {
  return_timestamps: 'word',
  chunk_length_s: 30,
  stride_length_s: 5,
});

console.log(result);
// { text: "Hello world", chunks: [{ text: "Hello", timestamp: [0.0, 0.5] }, ...] }

Model Files#

The model includes the following ONNX files in the onnx/ directory:

FileDescription
encoder_model.onnxAudio encoder (fp32)
decoder_model.onnxText decoder (fp32)
decoder_with_past_model.onnxDecoder with KV cache
decoder_model_merged.onnxMerged decoder for efficient inference
*_int8.onnxINT8 quantized versions
*_uint8.onnxUINT8 quantized versions

Acknowledgments#

Files

57 files · 26.2 GBWeights 181 MB (smallest of 34 ONNX variants). Sizes and sha256 from the signed manifest.
Show all 57 files with their sha256
FileSizesha256
.gitattributes1.52 KB11ad7efa24975ee4b0c3c3a38ed18737f0658a5f75a0a96787b576a78a023361
README.md1.82 KBf321b95caf27234f48bb522ae31109b103f26fb716affa4288de5f2b96a91db4
added_tokens.json34.6 KB560be47bea388757f8d4cc185c5d82067426cbb6361e38016dd90ddc01ab203a
config.json1.37 KBad31ca7a37eede52184e6b76d293f854b8f056c65189020e56e2fed9448b36c8
decoder_model.onnx1.83 GB417d1d3a1e88cdfb923fc51a5b90da69bcf7dec7a1e438f5374e55a792825d63
encoder_model.onnx1.23 GB1513207c339dc36fb1383751cad80f9d369b9a619a1168b19524bf7d3ae12971
generation_config.json1.97 KBadc5433fa7db17931299f430e5dcaf3995baf5218bcd577c9972db12314c97c3
merges.txt456 KB1ce1664773c50f3e0cc8842619a93edc4624525b728b188a9e0be33b7726adc5
normalizer.json52.7 KBbf1c507dc8724ca9cf9903640dacfb69dae2f00edee4f21ceba106a7392f26dd
onnx/added_tokens.json34.6 KB560be47bea388757f8d4cc185c5d82067426cbb6361e38016dd90ddc01ab203a
onnx/config.json2.21 KB862970859e5ebd3893d0901aab0bf6f45616fe0c83c7dbfbfc9baec7a26d62a6
onnx/decoder_model.onnx1.83 GB169e131a8458ae07959238e1eef50510469a2a33a9d22b01bdd633d97af0c2ae
onnx/decoder_model_bnb4.onnx443 MB5be53975b342a22c2508bda6da621232900955fae936cf3cb22c5a8aabda6e76
onnx/decoder_model_fp16.onnx914 MB5536edf7a370b070ba664d3c58c55294b562465a848b9354903a0aca4c86f56f
onnx/decoder_model_int8.onnx671 MB240c8efb21a490150a05635d4e1fb7719f1c795cc8ff85d696473e3e59e30f4d
onnx/decoder_model_merged.onnx1.83 GB10951976e19357aa93540da4cad90b2ec071d9c3f012cf996a38aa7ab543d5c7
onnx/decoder_model_merged_bnb4.onnx444 MB6527e55f0d0ee92a1c326664ddce0f0676c7d443cec3ad39fa65ef761d0a2453
onnx/decoder_model_merged_fp16.onnx915 MB7b9e3f3dfabd06b3b75986c4c18a5c2df647b3dd1118d6b1fd86a6bf0ccdd4a4
onnx/decoder_model_merged_int8.onnx1.83 GBcf0fe865e674aa014d9f719a58a429ce3590b1db3025c4c3b381fd6dbba54503
onnx/decoder_model_merged_q4.onnx469 MB18282746412f1ea287204cd012a2ae3c986a6a16b2e4d3c259f675be7cd7deb9
onnx/decoder_model_merged_q4f16.onnx336 MB34b9bf25d17d0b3fa202ed20fcc2e99e3fe4e389d8cf47588d1908c674fdff82
onnx/decoder_model_merged_quantized.onnx673 MB17fd842e10abc95beb453c7ac0184a339553e9dbba8f2fd17bef112e8d992d5b
onnx/decoder_model_merged_uint8.onnx1.83 GBcf0fe865e674aa014d9f719a58a429ce3590b1db3025c4c3b381fd6dbba54503
onnx/decoder_model_q4.onnx468 MBdb09e36f9d22c4d672ad7508bf4adf2b681d68354af39d12ed9e21c1529d0534
onnx/decoder_model_q4f16.onnx335 MB084d7f7d0631f696de2690debdd3a251ae730a7088475c789cce0fe1887b429f
onnx/decoder_model_quantized.onnx671 MB994b75b8114b160493080b94c6b67498ac7bf746f938446287b781367b23521f
onnx/decoder_model_uint8.onnx671 MBcfda2944e3d62ff2c362399b8e4e7f1f203a688a63928cf5ea6c53438641ad3d
onnx/decoder_with_past_model.onnx1.63 GBbe1a067ea718c759ec46c8225b96aaa40daf2c0185e585cc6717b38f3ac4b080
onnx/decoder_with_past_model_bnb4.onnx415 MBec18d8e53aa3d9c0eb57c349336e2f98bd1de531491ed1a737db24cb402c18a3
onnx/decoder_with_past_model_fp16.onnx813 MBca62780054e623620f1b735d05272a8530cee23c92f561916da58febbdc9465d
onnx/decoder_with_past_model_int8.onnx621 MB0414a50272960e5d3936a12639fdb853afcec7725b59ee072c527f26432750da
onnx/decoder_with_past_model_q4.onnx437 MB97a2c3ec1d1a85f9ef3ead3f3a24156e7b19a3470719a3dc9b881e110d6bbc82
onnx/decoder_with_past_model_q4f16.onnx307 MBbca44637c46ffa7b773654a650e42445cfbaf84a50ccdd11263eade115060046
onnx/decoder_with_past_model_quantized.onnx621 MB576b1021adad317cba609f5ef6e125506501ccbf0de3f704f83f25e2ce8028af
onnx/decoder_with_past_model_uint8.onnx621 MBfb4ec9964f7ef92f3feaf18d932c89ec794e9602c099551a4d81af7babb92dcf
onnx/encoder_model.onnx1.23 GBe2261b8c05ee58f62cca0bc7026f05c9cd66e9a3c03dbe8821f085fdce869f5c
onnx/encoder_model_bnb4.onnx191 MB370f7d76b6607ada12023ede86744bc6241dfa2adea2b1defa849f0da460c904
onnx/encoder_model_fp16.onnx615 MB34aa931f12bbb21b8b8499f540989ce0d9a5aba33e66946fa5e22a847847c27f
onnx/encoder_model_int8.onnx313 MB8f60f13597901a5d298338d9c7a976a01b02446a5adc7b0091558956e749609e
onnx/encoder_model_q4.onnx210 MBb231cee011c83eecc732ed72a63b12a5add1b7278314ca57da8797e213734228
onnx/encoder_model_q4f16.onnx181 MB32f2d7e1fd9db0f170917987ee402140fb657b14af47aaa4d61965b52d95316a
onnx/encoder_model_quantized.onnx313 MB4c1cc5ae608781afe378215a1f7c1201de97f2c63646380ebcae33d8349b3b66
onnx/encoder_model_uint8.onnx313 MBb129864ef121ac729f8ebfcfb586092908c7734720090b07b29cac5850b2dd64
onnx/generation_config.json1.94 KB63140c9c705f5cffafdad9601066503524eb0e3d88060e4c620eb9dd1da50dfe
onnx/merges.txt456 KB1ce1664773c50f3e0cc8842619a93edc4624525b728b188a9e0be33b7726adc5
onnx/normalizer.json52.7 KBbf1c507dc8724ca9cf9903640dacfb69dae2f00edee4f21ceba106a7392f26dd
onnx/preprocessor_config.json339 Ba6a76d28c93edb273669eb9e0b0636a2bddbb1272c3261e47b7ca6dfdbac1b8d
onnx/special_tokens_map.json2.17 KB98bdf3ec5b32e31575b02f64b0a32bde7c0449075d34484a7df9bdd3cdeb9fb9
onnx/tokenizer.json2.41 MB1bb34b47daba40728f488323190dc64765c5338b5196f95c4af926e13a6161c3
onnx/tokenizer_config.json283 KB93879c3dccdd4b976f709acd85b44778873f30c275e67026f30ca1e4c975230c
onnx/vocab.json999 KBf6bd25a65e4e63ca31360e9fb11c7e4f9a391a78385d640acd814092dd6eee4f
preprocessor_config.json339 Ba6a76d28c93edb273669eb9e0b0636a2bddbb1272c3261e47b7ca6dfdbac1b8d
quantize_config.json312 B70f61db8708568fa3ee6e66ecbcfdb8a89b9069feadff679dea00b097e521c98
special_tokens_map.json2.17 KB98bdf3ec5b32e31575b02f64b0a32bde7c0449075d34484a7df9bdd3cdeb9fb9
tokenizer.json3.86 MB287537d5be89a39bd18e7e3875ad9900faa668493fb759392b8f52a492eca5db
tokenizer_config.json283 KB7498445adabf4fd836db90b0f0d979ca9dc0b543528e5d9f1912430a5879e212
vocab.json999 KBf6bd25a65e4e63ca31360e9fb11c7e4f9a391a78385d640acd814092dd6eee4f
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
475d02b986 pinned now2026-11-15 05:18 UTC57 files · 26.2 GB

Use it

$ fw get onnx-community/whisper-medium.en_timestamped
# manifest sha256 3b56bde4ed50… · 26.2 GB · 57 files
$ fw verify ./whisper-medium.en_timestamped onnx-community/whisper-medium.en_timestamped
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/onnx-community/whisper-medium.en_timestamped.json --dir ./whisper-medium.en_timestamped $ python3 fw.py verify ./whisper-medium.en_timestamped ./onnx-community__whisper-medium.en_timestamped.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download onnx-community/whisper-medium.en_timestamped --revision 475d02b986111e8e2d28206d82e64bb820f5c6db --local-dir ./whisper-medium.en_timestamped

License

Name
MIT License
Id
MIT
Class
Permissive
Redistribution
yes
Listing
Hosted (signed)
Decided
License as declared by the publisher. No person read it. 2026-11-15
Text in
README.md
Text sha256
f321b95caf27234f48bb522ae31109b103f26fb716affa4288de5f2b96a91db4
Terms gate
No extra terms beyond the license.

Read the license text

Licenses are checked against the license table. A custom license passes only after a person reads it.

Provenance

From: onnx-community <huggingface.co/onnx-community>Newsgroups: alt.freeweights.speechSubject: whisper-medium.en_timestampedDate: 2026-11-15Commit: 475d02bSigned: 2DC28CC7B26A283B ✓
Upstream
onnx-community/whisper-medium.en_timestamped
Pinned commit
475d02b986111e8e2d28206d82e64bb820f5c6db
Manifest
whisper-medium.en_timestamped.json · .minisig
Manifest sha256
3b56bde4ed50f52dded1800780f795493926b76cc7bf1e3b7b1d899b585f2dcd
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 05:18 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/onnx-community/whisper-medium.en_timestamped.json $ curl -O https://freeweights.allternit.com/manifests/onnx-community/whisper-medium.en_timestamped.json.minisig $ minisign -Vm whisper-medium.en_timestamped.json -P RWQ7KGqyx4zCLXtUFOqvfv8L3g+8fpKJ1FsuxPyOYMF+4KufbUxKq1Oq $ shasum -a 256 <file> # compare with the Files tab

A manifest whose signature fails must be rejected. A file whose size or sha256 does not match must be discarded. Verify a download

Model tree

Parent

openai/whisper-medium.en · this model is a quantization of it

No model in the catalog names this one as its parent.

Get it
Download
$ HF_ENDPOINT=https://freeweights.allternit.com hf download onnx-community/whisper-medium.en_timestamped
Open in Freeweights Studio

Pull, verify and run it in the Allternit app on Desktop, web or phone.

Signed manifest
minisign, key 2DC28CC7B26A283B. whisper-medium.en_timestamped.json. Provenance. Takedown history: none.
From: MIT <huggingface.co/MIT>Subject: ast-finetuned-audioset-10-10-0.4593
From: onnx-community <huggingface.co/onnx-community>Subject: ast-finetuned-audioset-10-10-0.4593-ONNX
From: Edge0 <huggingface.co/Edge0>Subject: Audio8-TTS-Preview-0.6b
From: Edge0 <huggingface.co/Edge0>Subject: Audio8-TTS-Realistic-Air
From: facebook <huggingface.co/facebook>Subject: audiobox-aesthetics
From: mlx-community <huggingface.co/mlx-community>Subject: chatterbox-4bit