woqiang0515

S2TT wrong reults after SPEECH_TO_TEXT finetuning

4

Hi everyone, We attempted to fine-tune the SPEECH_TO_TEXT component using our domain-specific data. However, when we used the fine-tuned English ASR model for English-to-Arabic translation, it consistently generated English text...

GPU requirements

1

Could you please provide details about the model and the number of GPUs used in the script provided in the example? We used 8 V100 GPUs (32GB each), and batch...