Hi, I notice GPU mem usage keeps increasing during training
I'm training on 1x A5000 24GB, dataset ~300h contains of 0.2-49s audio files
My train.py settings:
batch_size_per_gpu = 1500
batch...
> Hi @v3ucn , thanks for PR~
>
> Will it also be compatible with `.read()` operations, or better serve as an option for compatibility of current users.
>
> Thanks again.
yes sir,It also wo...
https://github.com/SWivid/F5-TTS/discussions/57#discussioncomment-10959029
This is a good starting point, I'm currently following this to train for Vietnamese.
You'll need to edit vocab.txt to ...
Hi @v3ucn , thanks for PR~
Will it also be compatible with `.read()` operations, or better serve as an option for compatibility of current users.
Thanks again.
When reading csv files, Excel identifies the encoding by reading the BOM on the file header. If the file header has no BOM information, it will read according to the Unicode encoding by default. Th...
I am running on Windows. Using pyenv to set up a virtual environment and Python 3.10.11. I ran the two commands for installing pytorch and then ran the command to install requirements.txt. All...
Traceback (most recent call last):
File "inference-cli.py", line 19, in <module>
from model import CFM, DiT, MMDiT, UNetT
File "/opt/SWivid/F5-TTS/F5-TTS/model/__init__.py", line 7, in <...