pphu / musicgen-small

Generate music from a prompt or melody

  • Public
  • 161 runs
  • GitHub
  • Paper
  • License

If you haven’t yet trained a model on Replicate, you can read one of the following guides.

Pricing

Trainings for this model run on Nvidia T4 GPU hardware, which costs $0.000225 per second.

Create a training

Install the Python library:

pip install replicate

Then, run this to create a training with pphu/musicgen-small:65f6182b as the base model:

import replicate

training = replicate.trainings.create(
  version="pphu/musicgen-small:65f6182bfcbc05fc05a28c78f1fbb9ddd1d8fd4ff439f4d9043d6aa8cd515dc1",
  input={
    ...
  },
  destination=f"{username}/<destination-model-name>"
)

print(training)

Note that before you can create a training, you’ll need to create a model and use its name as the value for the destination field.