fish-speech-1.5-yth-lora

[rhfu]

python tools/llama/merge_lora.py
--lora-config r_8_alpha_16
--base-weight checkpoints/fish-speech-1.5
--lora-weight results/$project/checkpoints/step_000000010.ckpt
--output checkpoints/fish-speech-1.5-yth-lora/

After fine-tuning, how is the directory generated by checkpoints/fish-speech-1.5-yth-lora used in inference? Do you want to specify it during inference?

[Emersonksc]

python -m tools.webui
--llama-checkpoint-path "checkpoints/fish-speech-1.4"
--decoder-checkpoint-path "checkpoints/fish-speech-1.4/firefly-gan-vq-fsq-8x1024-21hz-generator.pth"
--decoder-config-name firefly_gan_vq
--compile
this is used for inferencing, and --llama-checkpoint-path is where your output directory should go, for your example: --llama-checkpoint-path "checkpoints/fish-speech-1.5-yth-lora/"

[cod3r0k]

I hear a beep sound after training. Why is this happening? After some iterations (about 2 days) during epoch 0, the process suddenly finished.
I checked the logs, and it just returned a beep sound. Why is this happening? The accuracy in the logs is 46%.