Tenzin Singhay Bhotia
Tenzin Singhay Bhotia
will help save unnecessary waste of time on a puny error, specially for beginners
Let's say the checkpoint is from the hugging-face training script. I want to transcribe using one of their checkpoints with this port.
I tried to run medium whisper fine-tuned models. 1. The standard open-ai models are fast. (infer in half the audio file time, 16threads, 1porcess) 2. Even the standard Hugging Face...
I want to benchmark streaming on a bunch of audio samples. It would be swift and efficient if the "stream" cli could input audio files and internally stream them. Can...