Fix for #703. Adds an optional sampleRate parameter to the decodeAudioToFloat32() function. The caption transcriber passes in a value of 16000 to prepare audio in the format Whisper expects. |
||
|---|---|---|
| .. | ||
| web | ||
Fix for #703. Adds an optional sampleRate parameter to the decodeAudioToFloat32() function. The caption transcriber passes in a value of 16000 to prepare audio in the format Whisper expects. |
||
|---|---|---|
| .. | ||
| web | ||
A Fortis Scientia site