open_model_zoo
distil-whisper
Our great sponsors
open_model_zoo | distil-whisper | |
---|---|---|
5 | 9 | |
3,945 | 3,125 | |
1.7% | 7.6% | |
8.6 | 8.5 | |
1 day ago | 11 days ago | |
Python | Python | |
Apache License 2.0 | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
open_model_zoo
- FLaNK Stack Weekly 06 Nov 2023
-
[D] Is BERT going to be obsolete by ChatGPT?
Search engines and chatbots are rapidly advancing with the introduction of ChatGPT, but search engines are still running on models like BERT (Bidirectional Encoder Representations from Transformers) for question-answer functionality. An interesting OpenVINO jupyter notebook #213 demonstrating question-answer functionality with a SQuAD v1.1 training set trained BERT model and transformer functions using either an embedded paragraph or a link to a website. I find it still really compelling to see how this works, basically how our widely used search engines function though on a much bigger scale.
- computer vision with Intel integrated GPU
- student in desperate need of help/ guidance
-
Openvino demos missing libraries
If not, below a github link https://github.com/openvinotoolkit/open_model_zoo/tree/master/demos/common/python
distil-whisper
- FLaNK Stack 05 Feb 2024
-
Distil-Whisper: a distilled variant of Whisper that is 6x faster
Training code will be released in the Distil-Whisper repository this week, enabling anyone in the community to distill a Whisper model in their choice of language!
- FLaNK Stack Weekly 06 Nov 2023
-
AI — weekly megathread!
Hugging Face released Distil-Whisper, a distilled version of Whisper that is 6 times faster, 49% smaller, and performs within 1% word error rate (WER) on out-of-distribution evaluation sets [Details].
- Distil-Whisper: distilled version of Whisper that is 6 times faster, 49% smaller
- Distil-Whisper is up to 6x faster than Whisper while performing within 1% Word-Error-Rate on out-of-distribution eval sets
-
Distilling Whisper on 20,000 hours of open-sourced audio data
- GitHub page: https://github.com/huggingface/distil-whisper/tree/main
-
Talk-Llama
Is https://github.com/huggingface/distil-whisper on its way to whisper.cpp?
What are some alternatives?
Face Recognition - The world's simplest facial recognition api for Python and the command line
WhisperInput - Offline voice input panel & keyboard with punctuation for Android.
deepstream-occupancy-analytics - This is a sample application for counting people entering/leaving in a building using NVIDIA Deepstream SDK, Transfer Learning Toolkit (TLT), and pre-trained models. This application can be used to build real-time occupancy analytics applications for smart buildings, hospitals, retail, etc. The application is based on deepstream-test5 sample application.
pyvideotrans - Translate the video from one language to another and add dubbing. 将视频从一种语言翻译为另一种语言,并添加配音
Dlib - A toolkit for making real world machine learning and data analysis applications in C++
vid2cleantxt - Python API & command-line tool to easily transcribe speech-based video files into clean text
faster-whisper - Faster Whisper transcription with CTranslate2
tensorflow-open_nsfw - Tensorflow Implementation of Yahoo's Open NSFW Model
json-masker - High-performance JSON masker library in Java with no runtime dependencies
openvino_notebooks - 📚 Jupyter notebook tutorials for OpenVINO™
willow - Open source, local, and self-hosted Amazon Echo/Google Home competitive Voice Assistant alternative