Hugging Face's logo

Spaces:
teticio
/
audio-diffusion
Runtime error

App Files Community
1
teticio commited on
Commit
3526755
•
1 Parent(s): c17b696

update README

Browse files
Files changed (1) hide show
  1. README.md +5 -5
README.md CHANGED
@@ -28,7 +28,7 @@ You can play around with the model I trained on about 500 songs from my Spotify
28
  #### Training can be run with Mel spectrograms of resolution 64x64 on a single commercial grade GPU (e.g. RTX 2080 Ti). The `hop_length` should be set to 1024 for better results.
29
 
30
  ```bash
31
- python audiodiffusion/audio_to_images.py \
32
  --resolution 64 \
33
  --hop_length 1024\
34
  --input_dir path-to-audio-files \
@@ -38,7 +38,7 @@ python audiodiffusion/audio_to_images.py \
38
  #### Generate dataset of 256x256 Mel spectrograms and push to hub (you will need to be authenticated with `huggingface-cli login`).
39
 
40
  ```bash
41
- python audiodiffusion/audio_to_images.py \
42
  --resolution 256 \
43
  --input_dir path-to-audio-files \
44
  --output_dir data-256 \
@@ -49,7 +49,7 @@ python audiodiffusion/audio_to_images.py \
49
 
50
  ```bash
51
  accelerate launch --config_file accelerate_local.yaml \
52
- audiodiffusion/train_unconditional.py \
53
  --dataset_name data-64 \
54
  --resolution 64 \
55
  --hop_length 1024 \
@@ -66,7 +66,7 @@ accelerate launch --config_file accelerate_local.yaml \
66
 
67
  ```bash
68
  accelerate launch --config_file accelerate_local.yaml \
69
- audiodiffusion/train_unconditional.py \
70
  --dataset_name teticio/audio-diffusion-256 \
71
  --resolution 256 \
72
  --output_dir ddpm-ema-audio-256 \
@@ -86,7 +86,7 @@ accelerate launch --config_file accelerate_local.yaml \
86
 
87
  ```bash
88
  accelerate launch --config_file accelerate_sagemaker.yaml \
89
- audiodiffusion/train_unconditional.py \
90
  --dataset_name teticio/audio-diffusion-256 \
91
  --resolution 256 \
92
  --output_dir ddpm-ema-audio-256 \
 
28
  #### Training can be run with Mel spectrograms of resolution 64x64 on a single commercial grade GPU (e.g. RTX 2080 Ti). The `hop_length` should be set to 1024 for better results.
29
 
30
  ```bash
31
+ python audio_to_images.py \
32
  --resolution 64 \
33
  --hop_length 1024\
34
  --input_dir path-to-audio-files \
 
38
  #### Generate dataset of 256x256 Mel spectrograms and push to hub (you will need to be authenticated with `huggingface-cli login`).
39
 
40
  ```bash
41
+ python audio_to_images.py \
42
  --resolution 256 \
43
  --input_dir path-to-audio-files \
44
  --output_dir data-256 \
 
49
 
50
  ```bash
51
  accelerate launch --config_file accelerate_local.yaml \
52
+ train_unconditional.py \
53
  --dataset_name data-64 \
54
  --resolution 64 \
55
  --hop_length 1024 \
 
66
 
67
  ```bash
68
  accelerate launch --config_file accelerate_local.yaml \
69
+ train_unconditional.py \
70
  --dataset_name teticio/audio-diffusion-256 \
71
  --resolution 256 \
72
  --output_dir ddpm-ema-audio-256 \
 
86
 
87
  ```bash
88
  accelerate launch --config_file accelerate_sagemaker.yaml \
89
+ strain_unconditional.py \
90
  --dataset_name teticio/audio-diffusion-256 \
91
  --resolution 256 \
92
  --output_dir ddpm-ema-audio-256 \