Ahmadzei's picture
added 3 more tables for large emb model
5fa1a76
raw
history blame contribute delete
511 Bytes
Since the original
target sequence length may be odd, the data collator makes sure to round the maximum length of the batch down to be a
multiple of 2.
data_collator = TTSDataCollatorWithPadding(processor=processor)
Train the model
Load the pre-trained model from the same checkpoint as you used for loading the processor:
from transformers import SpeechT5ForTextToSpeech
model = SpeechT5ForTextToSpeech.from_pretrained(checkpoint)
The use_cache=True option is incompatible with gradient checkpointing.