alt.freeweights.text / BUD-E-Whisper
From: laion <huggingface.co/laion>Newsgroups: alt.freeweights.textSubject:

BUD-E-Whisper

Date: 2026-11-15Commit: 9400e67Signed: 2DC28CC7B26A283B ✓

Automatic speech recognition model with 242M parameters. Safetensors weights, 969 MB in all. Published by laion under CC-BY-4.0.

242M params969MBBUD-E-Whispersafetensorspermissive
FactsParams242MSize969 MBFormatssafetensorsTaskautomatic speech recognitionLicenseCC-BY-4.0From sourcepermissive
$ fw get laion/BUD-E-Whisper
# manifest sha256 282525de6199… · 969 MB · 12 files
$ fw verify ./BUD-E-Whisper laion/BUD-E-Whisper
From sourceHosted (signed)laion/BUD-E-WhisperLast check: 2026-11-15 03:28 UTC

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

Works with

Overview

Size
969 MB
Weights
967 MB (safetensors)
Parameters
242M
Formats
safetensors
Task
automatic speech recognition
License
CC-BY-4.0 (permissive)
Files
12, each with a sha256
Publisher
laion
Added
2026-11-15
Section
alt.freeweights.text
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.co2026-11-15 03:28 UTCpassed

Model card

From the publisher at commit 9400e67. Shown as plain text with links; images open at the publisher.

BUD-E Whisper: Emotional Speech Captioning Model#

BUD-E Whisper is a suite of Whisper models fine-tuned for direct emotional speech captioning. The core models are built upon OpenAI's Whisper architecture, with the current primary variant being a fine-tune of OpenAI Whisper Small. These models are designed to generate text captions that not only transcribe speech but also inherently reflect its emotional content.

The embeddings generated by BUD-E Whisper can also serve as input for Empathic Insight - Voice, a downstream ensemble of Multi-Layer Perceptrons (MLPs) designed to predict dimensional emotion scores.

License#

This model is released under the CC-by-4.0 license. Please give attribution to Maurice Kraus & Christoph Schuhmann, who made this model.

Colab#

Open In Colab

Training Data#

BUD-E Whisper was trained on a combination of:

Training Procedure & Caption Generation#

A key aspect of BUD-E Whisper's development was a multi-step caption refinement process to create rich training targets:

  1. Initial Score Generation: An iterative process using Gemini Flash 2.0 generated initial 40-dimensional emotion scores (0-4 scale) and 15 additional dimensions like age, arousal, valence, dominance, harshness, vocalbursts,... for all audio snippets.
  2. Templated Captions: These scores were converted into templated string captions.
  3. Paraphrasing for Richness: Gemini Flash 2.0 was then used to paraphrase these templated captions, creating diverse and semantically rich training targets.
  4. Fine-tuning: Various Whisper model sizes (including the aforementioned fine-tune of OpenAI Whisper Small) were fine-tuned on these refined, emotionally-aware captions.

This multi-step caption refinement was crucial for performance. Direct score regression or simple templated captions were found to lead to suboptimal performance for emotional speech captioning with Whisper models.

Intended Use#

  • Generating emotionally nuanced captions for audio content.
  • Providing rich embeddings for downstream emotion recognition tasks (e.g., with Empathic Insight - Voice).

Files

12 files · 969 MBWeights 967 MB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 12 files with their sha256
FileSizesha256
.gitattributes1.52 KB11ad7efa24975ee4b0c3c3a38ed18737f0658a5f75a0a96787b576a78a023361
README.md2.62 KBddc3d16cd54153607314d9283b08aad8cc315c5184fd5af387c89ac1767144d8
added_tokens.json34.6 KB9715fd2243b6f06a5858b5e32950d2853f73dd5bc201aafcf76f5082a2d8acd1
config.json1.43 KB199b4ed36c036908f3b54b5bef47a04fd721587e2ed2c8e33a80369ace168a8f
generation_config.json3.84 KB445fa0dc13ccd9da93f91285f80eb92b1ab1ef7376a034a15a4c43f36ff62ec3
merges.txt494 KB2df2990a395e35e8dfbc7511e08c12d56018d8d04691e0133e5d63b21e154dc6
model.safetensors967 MB7bbd466bf003d717fcc17119bc2619165dba237aaf2b47bc727e494539c1351d
normalizer.json52.7 KBbf1c507dc8724ca9cf9903640dacfb69dae2f00edee4f21ceba106a7392f26dd
preprocessor_config.json339 Ba6a76d28c93edb273669eb9e0b0636a2bddbb1272c3261e47b7ca6dfdbac1b8d
special_tokens_map.json2.19 KBe67ae3a0aaa99abcd9f187138e12db1f65c16a14761c50ef10eef2c174a7a691
tokenizer_config.json283 KB21a4fc0483c14b87f4e0bbc177a9a357479bfa7c95aaf21ad53d71e9c5afafb9
vocab.json1.04 MB50d6a919f0a0601d56a04eb583c780d18553aa388254ba3158eb6a00f13e2c1a
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
9400e6740e pinned now2026-11-15 03:28 UTC12 files · 969 MB

Use it

$ fw get laion/BUD-E-Whisper
# manifest sha256 282525de6199… · 969 MB · 12 files
$ fw verify ./BUD-E-Whisper laion/BUD-E-Whisper
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/laion/BUD-E-Whisper.json --dir ./BUD-E-Whisper $ python3 fw.py verify ./BUD-E-Whisper ./laion__BUD-E-Whisper.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download laion/BUD-E-Whisper --revision 9400e6740ea103bf619a4ce66374576fab8a4e23 --local-dir ./BUD-E-Whisper
transformersSpeech recognition with the transformers pipeline.
import os os.environ["HF_ENDPOINT"] = "https://freeweights.allternit.com" from transformers import pipeline asr = pipeline("automatic-speech-recognition", model="laion/BUD-E-Whisper", revision="9400e6740ea103bf619a4ce66374576fab8a4e23") print(asr("audio.wav")["text"])

License

Name
Creative Commons Attribution 4.0
Id
CC-BY-4.0
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
ddc3d16cd54153607314d9283b08aad8cc315c5184fd5af387c89ac1767144d8
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: laion <huggingface.co/laion>Newsgroups: alt.freeweights.textSubject: BUD-E-WhisperDate: 2026-11-15Commit: 9400e67Signed: 2DC28CC7B26A283B ✓
Upstream
laion/BUD-E-Whisper
Pinned commit
9400e6740ea103bf619a4ce66374576fab8a4e23
Manifest
BUD-E-Whisper.json · .minisig
Manifest sha256
282525de61993b9762516df614a96e6cfdabcea74062fb42ed7938ce667d8c18
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 03:28 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/laion/BUD-E-Whisper.json $ curl -O https://freeweights.allternit.com/manifests/laion/BUD-E-Whisper.json.minisig $ minisign -Vm BUD-E-Whisper.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

1 model in the catalog name this one as their parent.

Fine-tunes
1
Fine-tunes 1
Get it
Download
$ HF_ENDPOINT=https://freeweights.allternit.com hf download laion/BUD-E-Whisper
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. BUD-E-Whisper.json. Provenance. Takedown history: none.
From: laion <huggingface.co/laion>Subject: a2-rl-e2egit_large-50-32B
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_e2egit-large-15-8B
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_e2egit-v2-10-8B
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_pymethods2test-large-80-8B
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_unitsyn-python-large-10-8B
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_mix_h2_language_proportional-65-8B