Whisper Distillation

community

https://github.com/huggingface/distil-whisper

Activity Feed Request to join this org

AI & ML interests

Robust knowledge distillation of the Whisper model via large-scale pseudo-labelling.

Recent Activity

eustlb authored a paper 12 days ago

Open ASR Leaderboard: Towards Reproducible and Transparent Multilingual and Long-Form Speech Recognition Evaluation

Steveeeeeeen authored a paper 15 days ago

Treble10: A high-quality dataset for far-field speech recognition, dereverberation, and enhancement

Steveeeeeeen authored a paper 15 days ago

Open ASR Leaderboard: Towards Reproducible and Transparent Multilingual and Long-Form Speech Recognition Evaluation

View all activity

distil-whisper 's collections 6

distil-large-v3.5

This collection contains the model repositories for distil-large-v3.5, which provides support for the most popular Whisper libraries.

distil-whisper/distil-large-v3.5

Automatic Speech Recognition • 0.8B • Updated Mar 25 • 5.04k • 74
distil-whisper/distil-large-v3.5-ct2

Automatic Speech Recognition • Updated Mar 19 • 1.6k • 5
distil-whisper/distil-large-v3.5-openai

Automatic Speech Recognition • Updated Mar 19
distil-whisper/distil-large-v3.5-ggml

Automatic Speech Recognition • Updated Mar 19 • 6

Training Datasets

A collection of pseudo-labelled datasets used to train the Distil-Whisper model.

distil-whisper/ami-ihm

Preview • Updated Sep 25, 2023 • 87
distil-whisper/ami-sdm

Updated Sep 25, 2023 • 54 • 1
distil-whisper/common_voice_13_0

Updated Sep 25, 2023 • 142 • 1
distil-whisper/gigaspeech-l

Updated Sep 25, 2023 • 126 • 1

Short-Form Test Sets

A collection of short-form (samples < 30s) datasets used to evaluate the Distil-Whisper models.

distil-whisper/earnings22

Viewer • Updated Oct 13, 2023 • 57.5k • 2.13k • 14
google/fleurs

Updated Aug 25, 2024 • 32.9k • 356
kensho/spgispeech

Updated Oct 21, 2022 • 1.82k • 33

distil-large-v3

This collection contains the model repositories for distil-large-v3, which provides support for the most popular Whisper libraries.

distil-whisper/distil-large-v3

Automatic Speech Recognition • 0.8B • Updated Mar 6 • 1.19M • 353
distil-whisper/distil-large-v3-ggml

Automatic Speech Recognition • Updated Mar 21, 2024 • 23
distil-whisper/distil-large-v3-ct2

Automatic Speech Recognition • Updated Mar 22, 2024 • 59 • 6
distil-whisper/distil-large-v3-openai

Automatic Speech Recognition • Updated Mar 27, 2024 • 4

Distil-Whisper Models

The first version of the Distil-Whisper models released with the Distil-Whisper paper.

Distil-Whisper: Robust Knowledge Distillation via Large-Scale Pseudo Labelling

Paper • 2311.00430 • Published Nov 1, 2023 • 57
distil-whisper/distil-large-v2

Automatic Speech Recognition • 0.8B • Updated Mar 6 • 7.81k • 511
distil-whisper/distil-medium.en

Automatic Speech Recognition • 0.4B • Updated Mar 25, 2024 • 20.1k • 125
distil-whisper/distil-small.en

Automatic Speech Recognition • 0.2B • Updated Mar 25, 2024 • 16.3k • 111

Long-Form Test Sets

A collection of long-form (samples > 30s) datasets used to evaluate the Distil-Whisper models.

distil-whisper/earnings21

Viewer • Updated Oct 13, 2023 • 44 • 146 • 3
distil-whisper/earnings22

Viewer • Updated Oct 13, 2023 • 57.5k • 2.13k • 14
distil-whisper/meanwhile

Viewer • Updated Oct 17, 2023 • 64 • 4.57k • 1
distil-whisper/rev16

Viewer • Updated Oct 17, 2023 • 46 • 122 • 1