VoiceStreamAI

VoiceStreamAI copied to clipboard

Client disconnects , and refreshes after the audio stream is recorded and sent to the server

5

hello @alesaccoia , thanks for the work on VoiceStreamAI , I was trying to make this work but , after setting the config and successfully establishing the websocket connection ,...

qxprakash

refactor code using black formatter and add dockerhub push cmd, and update base image to version containing cudnn8

6

FrostFlowerFairy

hallucinated words in the output

10

While running the program during silence periods irrelevant output like "okay" and "thank you" appears. Is there a way to fix this or is it a feature of faster-whisper

noah-george

I am using this code, but I have a question. src/buffering_strategy/buffering_strategies.py line:87 I can't understand why the following code is needed? `self.client.buffer.clear()` Please help me. Thank you.

AI-General

Remote dev container

3

xuwenhao

Wondering if the documentation of samples_width is correct here. https://github.com/alesaccoia/VoiceStreamAI/blob/465403b7039d1f54ba6b8d69c69c40b55bf300c1/src/server.py#L25 Because when calculating for buffer and scratch_buffer, there is no division by 8. https://github.com/alesaccoia/VoiceStreamAI/blob/465403b7039d1f54ba6b8d69c69c40b55bf300c1/src/buffering_strategy/buffering_strategies.py#L116-L118 https://github.com/alesaccoia/VoiceStreamAI/blob/465403b7039d1f54ba6b8d69c69c40b55bf300c1/src/buffering_strategy/buffering_strategies.py#L73-L77

kenho211

Unnecessary whitespace in Faster Whisper ASR output for Chinese

2

https://github.com/alesaccoia/VoiceStreamAI/assets/39730824/c86907e4-f6df-4bce-bf75-090ee34f7384

jinmiaoluo

how can I deploy with my local model (e.g. faster_whisper_large_v3)?

3

as title

ruifengma

audio from video element?

5

how to use audio chunks from a video element and transcribe it? thanks

ROBERT-MCDOWELL

Current UI: https://github.com/alesaccoia/VoiceStreamAI/assets/39730824/98cef236-7ed5-474c-b184-b082b8526df9 New UI: https://github.com/alesaccoia/VoiceStreamAI/assets/39730824/c997744b-63c9-4bc2-ad62-a537a06a8d96

jinmiaoluo