API endpoint URL
Alright, let me start out by saying I'm very new to all this and just trying to offload transcription for a specific program. I have setup an endpoint .. but the software config only asks for "endpoint url" . My question is, what do I put there so the transcription gets offloaded. As it is I just get a return of a 404 page not found.
--- Remote Settings (Only used if TRANSCRIPTION_MODE=remote) ---
URL of your running faster-whisper-server/speaches API
FASTER_WHISPER_SERVER_URL=https://api.runpod.ai/v2/myid/run # Ignored if mode is 'local'
10 Replies
I think you have to use custom api for faster whisper
GitHub
GitHub - runpod-workers/worker-faster_whisper: faster-whisper as se...
faster-whisper as serverless endpoint. Contribute to runpod-workers/worker-faster_whisper development by creating an account on GitHub.
heres the inputs available and an example below that
the software just asks for a url of the server running faster whisper, so do the serverless enpoints have an IP:port or maybe I should be using baremetal that does?
im not sure whats the software, did you mean pods? sure anything that works for your application
the serveless endpoints does support ip:port, but mainly it uses the /run or /runsync endpoint not ports
hrmm. Ok. as above I did try FASTER_WHISPER_SERVER_URL=https://api.runpod.ai/v2/myid/run but that just gave me a 404
what I'm trying to get working is this https://github.com/poisonednumber/Scanner-map
GitHub
GitHub - poisonednumber/Scanner-map
Contribute to poisonednumber/Scanner-map development by creating an account on GitHub.
yeah maybe it needs faster whisper api that is openai compatible
i believe the runpod one doesnt support that openai api
GitHub
GitHub - speaches-ai/speaches
Contribute to speaches-ai/speaches development by creating an account on GitHub.
I got it working with a pod. Thanks!