CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.speech / faster-whisper-medium.en
From: Systran <huggingface.co/Systran>Newsgroups: alt.freeweights.speechSubject:

faster-whisper-medium.en

Date: 2026-11-14Commit: a29b04bSigned: 2DC28CC7B26A283B ✓

Automatic speech recognition model. Ctranslate2 weights, 1.53 GB in all. Published by Systran under MIT.

speech1.53GBfaster-whisper-medium.enctranslate2permissive
FactsParamsnot statedSize1.53 GBFormatsctranslate2Taskautomatic speech recognitionLicenseMITFrom sourcepermissive
$ fw get Systran/faster-whisper-medium.en
# manifest sha256 391c902b4d37… · 1.53 GB · 6 files
$ fw verify ./faster-whisper-medium.en Systran/faster-whisper-medium.en
From sourceHosted (signed)Systran/faster-whisper-medium.enLast check: 2026-11-14 21:32 UTC
Get help

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

Works with

Run16
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
1.53 GB
Weights
see files
Parameters
not stated
Formats
ctranslate2
Task
automatic speech recognition
License
MIT (permissive)
Files
6, each with a sha256
Publisher
Systran
Added
2026-11-14
Section
alt.freeweights.speech
Lineage

Original release from the publisher.

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.co2026-11-14 21:32 UTCpassed

Model card

From the publisher at commit a29b04b. Shown as plain text with links; images open at the publisher.

Whisper medium.en model for CTranslate2#

This repository contains the conversion of openai/whisper-medium.en to the CTranslate2 model format.

This model can be used in CTranslate2 or projects based on CTranslate2 such as faster-whisper.

Example#

from faster_whisper import WhisperModel

model = WhisperModel("medium.en")

segments, info = model.transcribe("audio.mp3")
for segment in segments:
    print("[%.2fs -> %.2fs] %s" % (segment.start, segment.end, segment.text))

Conversion details#

The original model was converted with the following command:

ct2-transformers-converter --model openai/whisper-medium.en --output_dir faster-whisper-medium.en \
    --copy_files tokenizer.json --quantization float16

Note that the model weights are saved in FP16. This type can be changed when the model is loaded using the compute_type option in CTranslate2.

More information#

For more information about the original model, see its model card.

Files

6 files · 1.53 GB Sizes and sha256 from the signed manifest.
Hide all 6 files with their sha256
FileSizesha256
.gitattributes1.48 KBdb7c0371f46f0840b8f25794c1e3321c9b5820a8cb6ba9694a46fc64b8fae5a6
README.md1.34 KBab3ddd3b6af4ea0ef353cb80004f26613ba33217f81652fc13738d3b098c7675
config.json2.64 KB4a1848ebabe7938d9797c15a2e8e4ce1d36e6fd4a43d096ae5955257c67c7962
model.bin1.53 GB11b220779aea4c6f3ce9d2549c8a95ea869ed84066864b999531ef53e594fe5b
tokenizer.json2.13 MB929c5252409436dce1b38a75d1abbcb5e132d170d8e324e4e04ed915fa2d22df
vocabulary.txt422 KBff77588746d3a2595d32ab5b69ffd7b95ce2441ac57533cb66fc3eb575a115cf
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
a29b04bd15 pinned now manifest updated, same commit2026-11-14 21:32 UTC6 files · 1.53 GB
a29b04bd152026-11-14 21:32 UTC6 files · 1.53 GB

Use it

$ fw get Systran/faster-whisper-medium.en
# manifest sha256 391c902b4d37… · 1.53 GB · 6 files
$ fw verify ./faster-whisper-medium.en Systran/faster-whisper-medium.en
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/Systran/faster-whisper-medium.en.json --dir ./faster-whisper-medium.en $ python3 fw.py verify ./faster-whisper-medium.en ./Systran__faster-whisper-medium.en.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download Systran/faster-whisper-medium.en --revision a29b04bd15381511a9af671baec01072039215e3 --local-dir ./faster-whisper-medium.en

License

Name
MIT License
Id
MIT
Class
Permissive
Redistribution
yes
Listing
Hosted (signed)
Decided
License as declared by the publisher. No person read it. 2026-11-14
Text in
README.md
Text sha256
ab3ddd3b6af4ea0ef353cb80004f26613ba33217f81652fc13738d3b098c7675
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: Systran <huggingface.co/Systran>Newsgroups: alt.freeweights.speechSubject: faster-whisper-medium.enDate: 2026-11-14Commit: a29b04bSigned: 2DC28CC7B26A283B ✓
Upstream
Systran/faster-whisper-medium.en
Pinned commit
a29b04bd15381511a9af671baec01072039215e3
Manifest
faster-whisper-medium.en.json · .minisig
Manifest sha256
391c902b4d37cade98233bc4c30c717b8d5b6cbf20fc5f5f6e8f1886f46dc555
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-14 21:32 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/Systran/faster-whisper-medium.en.json $ curl -O https://freeweights.allternit.com/manifests/Systran/faster-whisper-medium.en.json.minisig $ minisign -Vm faster-whisper-medium.en.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

No related models in this catalog.Nothing here lists this model as its parent, and it names no parent.
Get it
Download
$ HF_ENDPOINT=https://freeweights.allternit.com hf download Systran/faster-whisper-medium.en
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. faster-whisper-medium.en.json. Provenance. Takedown history: none.
Source
huggingface.co/Systran/faster-whisper-medium.en

Related models

All of alt.freeweights.speech →
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