Text-to-Audio
Transformers
Diffusers
Safetensors
ACE-Step
feature-extraction
audio
music
text2music
custom_code
Instructions to use ACE-Step/Ace-Step1.5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ACE-Step/Ace-Step1.5 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-audio", model="ACE-Step/Ace-Step1.5", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("ACE-Step/Ace-Step1.5", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
What time it takes to train on a RTX 4090 24GB
#29
by Bidram - opened
Hello, i have near ~8,000 full-lyrics track of music i wanted to Fine-Tune the base model on, i wanted to know what maximum epoch is best, how much it could take for the training, and at last, can i increase the batch size of training to 16+? because in the prices of GPU cloud, GPUs like RTX 6000 42GB were cheaper, so i thought if i could increase the batch size for faster training.