You're looking at a specific version of this model. Jump to the model overview.
xavriley /sax_transcription:a0d3bd7b
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 |
|---|---|---|---|
| audio_input |
string
|
Piano audio to transcribe
|
|
| beats_per_bar |
integer
|
0
|
numerator for time signature, default: 4
|
| model_path |
string
|
./model.pth
|
Optional URL to specify different model weights
|
| syncpoints_path |
string
|
Optional path to syncpoints file
|
|
| midi_path |
string
|
Option path to midi file - skips audio and runs score layout only
|
|
| start_time |
number
|
0
|
Start time for audio
|
| finish_time |
number
|
0
|
Finish time for audio
|
| skip_separation |
boolean
|
False
|
Skip separation step
|
| file_label |
string
|
Optional label for output filename
|
|
| yt_url |
string
|
Optional YouTube URL to fetch audio from - replaces audio_input
|
|
| device |
string
|
cuda
|
Device to run inference on
|
Output schema
The shape of the response you’ll get when you run this model with an API.
Schema
{'title': 'Output'}