vosk-browser
cheetah
| vosk-browser | cheetah | |
|---|---|---|
| 3 | 5 | |
| 326 | 555 | |
| - | 0.7% | |
| 0.0 | 8.2 | |
| 4 months ago | 1 day ago | |
| JavaScript | 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.
vosk-browser
-
Show HN: I record myself on audio 24x7 and use an AI to process the information
Not the OP but I've been tinkering with the same concept (24/7 processing).
'm using vosk browser: https://github.com/ccoreilly/vosk-browser
To do speech to text locally and it works very well for English.
- Speech-to-Text Client-Side?
-
On-device browser translations with Firefox Translations
I believe this is called the Bergamot project, more can be found here: https://browser.mt/
The GitHub repo for it is here: https://github.com/browsermt/bergamot-translator
The repo contains some details about how to run it in WASM which is quite interesting for embedding it in pages. I've been playing around with using WASM to capture speech to text (https://github.com/ccoreilly/vosk-browser) and automatically translating it using Bergamot.
Results have been, ok. I don't think the tech is quite there yet and the speech to text obviously struggles with multiple speakers.
cheetah
-
voice-to-text-notes VS cheetah - a user suggested alternative
2 projects | 8 Oct 2022
Picovoice processes voice data locally on device without sending it to the cloud. Hence, nobody has access to the data other than the owner, making it 100% private. It is more accurate than Google or IBM. Offers 100 hours of free transcription per month.
-
Transcribe Speech to Text with Python for Free
Cool! Leopard operates on files but Cheetah can do live (streaming)
-
Voice to Text Options that respect privacy
I already knew pocketsphinx or Mozilla DeepSpeech, but Picospeech Cheetah is probably the best, offline, STT system currently.
- ELI5: Why do we wake up when we hear our names?
-
Control a Java application with offline voice commands - source code in comments!
Looks really interesting. Can you explain the license? It is not clear to me as Cheetah (the underlying speech to text engine?) is not open source but this SDK is which requires Cheetah?
What are some alternatives?
vosk-api - Offline speech recognition API for Android, iOS, Raspberry Pi and servers with Python, Java, C# and Node
silero-vad - Silero VAD: pre-trained enterprise-grade Voice Activity Detector
vosk-server - WebSocket, gRPC and WebRTC speech recognition server based on Vosk and Kaldi libraries
picovoice - On-device voice assistant platform powered by deep learning
ovos-stt-plugin-vosk - vosk STT plugin for mycroft
react-native-vosk - Speech recognition module for react native using Vosk library
rhino - Rhino is an open-source implementation of JavaScript written entirely in Java
haven - Haven is for people who need a way to protect their personal spaces and possessions without compromising their own privacy, through an Android app and on-device sensors
rhino - On-device Speech-to-Intent engine powered by deep learning
whisper - Robust Speech Recognition via Large-Scale Weak Supervision
psdb - Python flasher and gdb server for various ARM debug probes.