Home› Projects› whisper-timestamped
whisper-timestamped
Python

whisper-timestamped

Multilingual Automatic Speech Recognition with word-level timestamps and confidence

by linto-ai · GitHub
2.8k
Stars
211
Forks
AGPL-3.0
License
2023
Created
11 mo ago
Last commit
asr
Category
Python
Language
asrattention-is-all-you-needattention-mechanismAGPL-3.0Python
View on GitHub
In plain words

Transcribe speech in multiple languages while getting word-level timestamps and confidence scores.

You maintain this project?

Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.

Claim this page →
whisper-timestamped — GitHub preview card
📈 Star history
2.83k2.82k
2026-07-072026-08-31
📈 Track whisper-timestamped

Get an email alert on its next release or when it starts trending — never miss the moment.

Free · no card · unsubscribe anytime
Get email alerts →
📄 About

Multilingual Automatic Speech Recognition with word-level timestamps and confidence

whisper-timestamped has 2.8k stars on GitHub. It has been forked 211 times. whisper-timestamped is written mainly in Python. It has been in active development since 2023. whisper-timestamped is available under the AGPL-3.0 license. Its main topics are asr, attention-is-all-you-need, attention-mechanism, attention-model.

❓ Frequently asked questions

What is whisper-timestamped?

Multilingual Automatic Speech Recognition with word-level timestamps and confidence

Is whisper-timestamped open source?

whisper-timestamped is an open-source project. It is released under the AGPL-3.0 license.

Is whisper-timestamped free?

Yes. whisper-timestamped is free and open source — you can use, modify and self-host it. Its AGPL-3.0 license is a strong copyleft: if you distribute a modified version — including offering it as a network service — your changes must be released under the same license.

What license does whisper-timestamped use?

whisper-timestamped is available under the AGPL-3.0 license.

What language is whisper-timestamped written in?

whisper-timestamped is written mainly in Python.

🏅 Maintainer of this project?
olud.ai badge — whisper-timestamped

Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.

[![olud.ai](https://olud.ai/badge.php?tool=linto-ai-whisper-timestamped)](https://olud.ai/project/linto-ai-whisper-timestamped.html)
More badge options →
🧬 Shares DNA with🧬 View the DNA map →
keras-attention
Keras Attention Layer (Luong and Bahdanau scores).
★ 2.8k · attention-mechanism
sharesattention-modelattention-mechanism
pytorch-original-transformer
My implementation of the original transformer model (Vaswani et al.). I've additionally include…
★ 1.1k · attention
sharesattention-is-all-you-needattention-mechanism
PALM-E
Implementation of "PaLM-E: An Embodied Multimodal Language Model"
★ 338 · artificial-intelligence
sharesattention-is-all-you-needattention-mechanism
zeta
Build high-performance AI models with modular building blocks
★ 597 · attention-mechanism
sharesattention-modelattention-mechanism
kospeech
Open-Source Toolkit for End-to-End Korean Automatic Speech Recognition leveraging PyTorch and H…
★ 637 · asr
sharesattention-is-all-you-needasr
neural_sp
End-to-end ASR/LM implementation with PyTorch
★ 594 · asr
sharesattention-mechanismasr
llm-internals
Learn LLM internals step by step - from tokenization to attention to inference optimization.
★ 1.5k · attention-is-all-you-need
sharesattention-is-all-you-needattention-mechanism
tensorflow_end2end_speech_recognition
End-to-End speech recognition implementation base on TensorFlow (CTC, Attention, and MTL traini…
★ 314 · asr
sharesattention-mechanismasr
attention-is-all-you-need-pytorch
A PyTorch implementation of the Transformer model in "Attention is All You Need".
★ 9.8k · attention
sharesattention-is-all-you-need
awesome-attention-mechanism-in-cv
Awesome List of Attention Modules and Plug&Play Modules in Computer Vision
★ 1.3k · attention-mechanisms
sharesattention-model

Measured from GitHub topics shared by both projects, weighted by how rare each topic is.