speech-to-text-benchmark
leopard
| speech-to-text-benchmark | leopard | |
|---|---|---|
| 5 | 15 | |
| 654 | 457 | |
| 0.6% | 0.2% | |
| 4.6 | 8.1 | |
| 10 days ago | 6 days ago | |
| Python | Python | |
| Apache License 2.0 | Apache License 2.0 |
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.
speech-to-text-benchmark
- Speech-to-Text Benchmark
-
Making a Podcast Transcription Server with Express.js (source code in comments)
Even better than my experience, there's an open-source benchmark!
-
DeepSpeech 60x Smaller, 9x faster, and 2x accuracy
The Mozilla DeepSpeech tests on LibreSpeech listed in your link were out of date back in 2020[1], and Coqui.ai (the continuation of Mozilla DeepSpeech) isn't even benchmarked.
https://github.com/Picovoice/speech-to-text-benchmark/issues...
- I got banned for using some Chinese swear words to some Chinese player and i was insta Voice banned
leopard
-
Automatic Speech Recognition with AWS Lambda and Leopard
Take a look at Leopard GitHub Repository or Leopard Docs Page to learn more about Leopard.
-
Day 19: Local Transcription w .NET
Looking for more: Open-source demo code Leopard GitHub repository Speech-to-text Benchmark
-
Day 13: Voice Recognition with Ubuntu
Voila! Reach out to Picovoice team on GitHub if you have any questions
-
Day 8: Making Cool Raspberry Pi Projects even Cooler with Voice AI (3/4)
This tutorial is intended for Raspberry Pi 4. If you're looking for Raspberry Pi 3 or Raspberry Pi 400 or Raspberry Pi 4 (64-bit) check out Leopard C Demos on GitHub
-
Day5: Building a local audio transcription engine running on your web browser with JavaScript
2. Serving the Model Leopard is an on-device speech-to-text solution. So we need to transfer the model (deep neural network) to the client to enable voice processing within the browser.
-
Making a Podcast Transcription Server with Express.js and Picovoice Leopard
How does Picovoice Leopard compare to other speech-to-text options?
https://github.com/Picovoice/leopard
-
Making a Podcast Transcription Server with Express.js (source code in comments)
Check out the source code here
- On-device speech-to-text engine powered by deep learning
- [P] On-device speech-to-text engine powered by deep learning
- picovoice/leopard - DeepSpeech 60x Smaller, 9x faster, and 2x accuracy
What are some alternatives?
FedML - FEDML - The unified and scalable ML library for large-scale distributed training, model serving, and federated learning. FEDML Launch, a cross-cloud scheduler, further enables running any AI jobs on any GPU cloud or on-premise cluster. Built on this library, TensorOpera AI (https://TensorOpera.ai) is your generative AI platform at scale.
werpy - 🐍📦 Ultra-fast Python package for calculating and analyzing the Word Error Rate (WER). Built for the scalable evaluation of speech and transcription accuracy.
vosk-build-model - How to create your own model for vosk
STT-examples - 🐸STT integration examples
transcribrr - Transcribrr is a python desktop application that uses transcribes audio/video files or youtube videos and summarizes the output using a variety of preset prompts using OpenAI's GPT models.