Random garbled fragments of non-existent word output, with same input different gibberish on different runs
#25
by
k1-m
- opened
While I got build up without errors locally on windows PC,
Only random garbled fragments are audible and with each run for same input text, different garbled short audio is generated!
Tried with exact reference audio from the Indicf5 prompts and the exact reference text.
Also tried 2 different language input text s but the garbled short audio generation is NOT fixed.
Please let us know if this model works for Telugu language audio generation from text