Closed kynthesis closed 1 year ago
For anyone who encountered the same issue, the speaker_number should start from 0 instead of 1.
Incorrect list.txt
...
./vivos/VIVOSSPK29/VIVOSSPK29_125.wav|29
./vivos/VIVOSSPK29/VIVOSSPK29_123.wav|29
./vivos/VIVOSSPK27/VIVOSSPK27_096.wav|27
./vivos/VIVOSSPK01/VIVOSSPK01_R051.wav|1
./vivos/VIVOSSPK01/VIVOSSPK01_R161.wav|1
./vivos/VIVOSSPK27/VIVOSSPK27_094.wav|27
./vivos/VIVOSSPK01/VIVOSSPK01_R033.wav|1
./vivos/VIVOSSPK01/VIVOSSPK01_R011.wav|1
./vivos/VIVOSSPK02/VIVOSSPK02_R035.wav|2
./vivos/VIVOSSPK01/VIVOSSPK01_R092.wav|1
...
Correct list.txt
...
./vivos/VIVOSSPK29/VIVOSSPK29_125.wav|28
./vivos/VIVOSSPK29/VIVOSSPK29_123.wav|28
./vivos/VIVOSSPK27/VIVOSSPK27_096.wav|26
./vivos/VIVOSSPK01/VIVOSSPK01_R051.wav|0
./vivos/VIVOSSPK01/VIVOSSPK01_R161.wav|0
./vivos/VIVOSSPK27/VIVOSSPK27_094.wav|26
./vivos/VIVOSSPK01/VIVOSSPK01_R033.wav|0
./vivos/VIVOSSPK01/VIVOSSPK01_R011.wav|0
./vivos/VIVOSSPK02/VIVOSSPK02_R035.wav|1
./vivos/VIVOSSPK01/VIVOSSPK01_R092.wav|0
...
Thank you for this fantastic project!
I tried to train on my custom dataset, then got some weird runtime errors. All setups are the same as the original repo except a custom config file and a custom dataset. The size of the dataset is quite small so I have directly added it into my repo. You can clone my repo if you want: https://github.com/kynthesis/StarGANv2-VNVC (https://github.com/kynthesis/StarGANv2-VNVC/commit/bf969b63c7c7fe6a0b74f7ff20193e9111959641)
On the same Python environment (python 3.8 and3.9), errors only occur on my custom dataset, original dataset is totally fine.
num_domains
is set4
, and the custom dataset is converted from 16000 Hz to 24000 Hz using Voxengo r8brain Free.My custom config:
config_vivos.yml
My custom dataset (converted from 16000 Hz to 24000 Hz) -> google drive ~ vivos lite ~ 200MB
Encountered runtime error
I really hope that you can take a look at this issue! Khoa