-
|
Hi, I tried running the very simple Python script in the readme on a very short 7 second MP3, and it takes about 15 seconds to return the transcript. Is that speed normal? Or is there something wrong with my setup? |
Beta Was this translation helpful? Give feedback.
Replies: 1 comment 2 replies
-
|
Yes it's about the expected throughput, especially if you're running on a CPU. The model loading part is probably taking the majority of the time, and you can transcribe multiple files once the model is loaded. |
Beta Was this translation helpful? Give feedback.
-
|
It's probably the loading of the model, you're right. How do you tell if it is running on the CPU or GPU? |
Beta Was this translation helpful? Give feedback.
-
|
|
Beta Was this translation helpful? Give feedback.
Yes it's about the expected throughput, especially if you're running on a CPU. The model loading part is probably taking the majority of the time, and you can transcribe multiple files once the model is loaded.