Damien Laine
Damien Laine
Greetings, Seems like these MFCC extraction utilities functions relies a constant which is set to 1125 in Meyda's implementation. I observed slight diferences between Meyda's and expected test results on...
- [ ] Introduce feature menu "Speech Processing" - [ ] Use relevant NLP API for Keyword identification - [ ] Associate them to a highlight with a "keyword" type
Deployment of Conversation Manager in public beta, packing up developed features - Public availability for front-end an websocket server **source code and Docker Images** - developers would run Docker images...
Compile our transcription runtime to wasm Allow **transcription services** to get cloned and used localy in a browser with wasm Allow models to get streamed and cloned localy in a...
- [x] Publish new Diarization Docker - [x] Test it - [x] Deploy on Customer's infra
The current Dockerfile for the application does not allow dynamic customization of the runtime user and group, making it less flexible for deployment in diverse environments. Running the container as...
# Whisper Streaming - Buffer Audio & Incorrect Finals ## **Description** While testing streaming functionality using Whisper, we have identified two principal issues: --- ## **1. Missing Buffer/Flush Mechanism** When...
## **Description** When using `SERVICE_MODE=websocket`, the current implementation does not properly handle health checks, leading healthcheck fail streak in orchestrated deployments. --- ## **Current Behavior** - Health checks fail when...
see https://github.com/linto-ai/linto-studio-plugins/issues/5