Comments (6)
It would be nice to have an option to use a API for whisper transcriptions. Should be fairly straight forwards since we can use this
https://platform.openai.com/docs/guides/speech-to-text/speech-to-text-beta. I will create a specific issue for this.
from ecoute.
I've been using whisper with a M2 with good results using this: openai/whisper#382
from ecoute.
You can check out this branch https://github.com/SevaSk/ecoute/tree/29-add-option-to-use-speech-to-text-api-rather-than-transcribing-locally
use the command
python main.py --api
it honestly way faster and better then the local model
edit:
merged that branch to main now.
from ecoute.
Thanks! If the transcription is slow, most likely culprit would be if this logging message:
print(f"[INFO] Whisper using GPU: " + str(torch.cuda.is_available()))
is false. Then Whisper cannot transcript with the GPU and will use the CPU instead, which is way slower.
Outside of using whisper, none of the code should run noticeably slow on any OS or computer.
from ecoute.
Agree.
torch.cuda.is_available() is only true with Nvida CUDA system, any AMD, Intel or other embedded GPU would not by default support it.
Would you consider integrate Whisper online API to not rely on local resource? Consider LangChain?
from ecoute.
Thanks for sharing and the work, on my way to try.
from ecoute.
Related Issues (20)
- Incorrect API key provided its showing
- NumbaDeprecationWarning and FFmpeg Installation Error in Whisper Module
- When i type "cd ecoute" Its is saying that it cannot find the file HOT 1
- Feature Request: use ChatGPT-4 HOT 2
- Feature Request: Send specific question to ChatGPT HOT 1
- Would able to disable Mic as input, just want speaker as input HOT 1
- python main.py error
- How is ecoute better than Transcribe repo HOT 2
- Issue while running
- python main.py -> ModuleNotFoundError: No module named 'torch._prims_common' HOT 1
- How to change the OpenAI interface address HOT 1
- ModuleNotFoundError: No module named 'whisper'. MAC OS HOT 1
- module 'ffmpeg' has no attribute 'Error'
- Unable to install ecoute with Python 3.12 version.Getting various errors. HOT 3
- Torch library dependent file issue
- Nothing happens after upload
- Only record microphone/speaker input on keypress
- Issue with the GPTResponsder + quota of chatgpt HOT 2
- No Module Name pyaudiowpatch
- python main.py when given this command not working its paid API key HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from ecoute.