You're looking at a specific version of this model. Jump to the model overview.
simpletuner /minimax-music3:64df7edd
Input schema
The fields you can use to run this model with an API. If you don’t give a value for a field its default value will be used.
| Field | Type | Default value | Description |
|---|---|---|---|
| train_data |
string
|
ZIP or tar containing stem-matched audio, .txt captions, and .lyrics files
|
|
| regularisation_data |
string
|
Optional unrelated-song archive used for frozen-base prior preservation
|
|
| trigger_word |
string
|
|
Optional keyword used as the prompt for every training track
|
| max_train_steps |
integer
|
750
Min: 1 Max: 5000 |
Optimizer steps
|
| checkpoint_interval |
integer
|
250
Min: 10 Max: 1000 |
Save every N steps
|
| lora_rank |
None
|
64
|
LoRA rank
|
| learning_rate |
number
|
0.00008
Min: 0.000001 Max: 0.0005 |
Constant learning rate
|
| max_audio_duration |
integer
|
180
Min: 10 Max: 300 |
Maximum token sequence duration per track in seconds
|
| seed |
integer
|
42
|
Training seed
|
Output schema
The shape of the response you’ll get when you run this model with an API.
Schema
{'format': 'uri', 'title': 'Output', 'type': 'string'}