Hugging Face's logo

google
/
music-spectrogram-diffusion

Diffusers
ONNX
PyTorch
SpectrogramDiffusionPipeline
Model card Files
xet
 Community
2
kashif HF Staff commited on
Commit
6786dba
·
1 Parent(s): 1d9603c

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -2
README.md CHANGED
@@ -23,13 +23,15 @@ As depicted above the model takes as input a MIDI file and tokenizes it into a s
23
  ## Example usage
24
 
25
  ```python
26
- from diffusers import SpectrogramDiffusionPipeline
27
 
28
  pipe = SpectrogramDiffusionPipeline.from_pretrained("google/music-spectrogram-diffusion")
29
  pipe = pipe.to("cuda")
30
 
31
  # Download via: wget http://www.piano-midi.de/midis/beethoven/beethoven_hammerklavier_2.mid
32
- output = pipe("beethoven_hammerklavier_2.mid")
 
 
33
 
34
  audio = output.audios[0]
35
  ```
 
23
  ## Example usage
24
 
25
  ```python
26
+ from diffusers import SpectrogramDiffusionPipeline, MidiProcessor
27
 
28
  pipe = SpectrogramDiffusionPipeline.from_pretrained("google/music-spectrogram-diffusion")
29
  pipe = pipe.to("cuda")
30
 
31
  # Download via: wget http://www.piano-midi.de/midis/beethoven/beethoven_hammerklavier_2.mid
32
+ processor = MidiProcessor()
33
+
34
+ output = pipe(processor("beethoven_hammerklavier_2.mid"))
35
 
36
  audio = output.audios[0]
37
  ```