Hugging Face's logo

Spaces:
pyp1
/
VoiceCraft_gradio
Running on A10G

App Files Community
5
jason-on-salt-a40 commited on
Commit
3075679
•
1 Parent(s): 9227743

updated libs for easier installation, cannot upload audio, recorded audio doesn't work

Browse files
Files changed (14) hide show
  1. README.md +5 -0
  2. app.py +3 -3
  3. data/__pycache__/__init__.cpython-310.pyc +0 -0
  4. data/__pycache__/tokenizer.cpython-310.pyc +0 -0
  5. models/__pycache__/codebooks_patterns.cpython-310.pyc +0 -0
  6. models/__pycache__/voicecraft.cpython-310.pyc +0 -0
  7. models/modules/__pycache__/__init__.cpython-310.pyc +0 -0
  8. models/modules/__pycache__/activation.cpython-310.pyc +0 -0
  9. models/modules/__pycache__/embedding.cpython-310.pyc +0 -0
  10. models/modules/__pycache__/scaling.cpython-310.pyc +0 -0
  11. models/modules/__pycache__/transformer.cpython-310.pyc +0 -0
  12. models/modules/__pycache__/utils.cpython-310.pyc +0 -0
  13. pretrained_models/giga830M.pth +3 -0
  14. requirements.txt +2 -5
README.md CHANGED
@@ -11,3 +11,8 @@ license: cc-by-nc-sa-4.0
11
  ---
12
 
13
  Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
 
 
 
 
 
 
11
  ---
12
 
13
  Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
14
+
15
+ ```bash
16
+ conda create -n voicecraft_gradio python=3.10.13
17
+ pip install -r requirements.txt
18
+ ```
app.py CHANGED
@@ -1,6 +1,6 @@
1
  import os
2
  # os.environ["CUDA_DEVICE_ORDER"] = "PCI_BUS_ID"
3
- # os.environ["CUDA_VISIBLE_DEVICES"] = "5" # these are only used if developping locally
4
  import gradio as gr
5
  import torch
6
  import torchaudio
@@ -381,7 +381,7 @@ with gr.Blocks() as app:
381
 
382
  with gr.Row():
383
  with gr.Column(scale=2):
384
- input_audio = gr.Audio(value="./demo/84_121550_000074_000000.wav", label="Input Audio", type="filepath")
385
  with gr.Group():
386
  original_transcript = gr.Textbox(label="Original transcript", lines=5, value=demo_original_transcript, interactive=False,
387
  info="Use whisper model to get the transcript. Fix it if necessary.")
@@ -469,7 +469,7 @@ with gr.Blocks() as app:
469
  inputs=[whisper_model_choice, voicecraft_model_choice],
470
  outputs=[models_selector])
471
 
472
- input_audio.upload(fn=update_input_audio,
473
  inputs=[input_audio],
474
  outputs=[prompt_end_time, edit_start_time, edit_end_time])
475
  transcribe_btn.click(fn=transcribe,
 
1
  import os
2
  # os.environ["CUDA_DEVICE_ORDER"] = "PCI_BUS_ID"
3
+ # os.environ["CUDA_VISIBLE_DEVICES"] = "1" # these are only used if developping locally
4
  import gradio as gr
5
  import torch
6
  import torchaudio
 
381
 
382
  with gr.Row():
383
  with gr.Column(scale=2):
384
+ input_audio = gr.Audio(sources=["upload", "microphone"], value="./demo/84_121550_000074_000000.wav", label="Input Audio", type="filepath", interactive=True)
385
  with gr.Group():
386
  original_transcript = gr.Textbox(label="Original transcript", lines=5, value=demo_original_transcript, interactive=False,
387
  info="Use whisper model to get the transcript. Fix it if necessary.")
 
469
  inputs=[whisper_model_choice, voicecraft_model_choice],
470
  outputs=[models_selector])
471
 
472
+ input_audio.change(fn=update_input_audio,
473
  inputs=[input_audio],
474
  outputs=[prompt_end_time, edit_start_time, edit_end_time])
475
  transcribe_btn.click(fn=transcribe,
data/__pycache__/__init__.cpython-310.pyc CHANGED
Binary files a/data/__pycache__/__init__.cpython-310.pyc and b/data/__pycache__/__init__.cpython-310.pyc differ
 
data/__pycache__/tokenizer.cpython-310.pyc CHANGED
Binary files a/data/__pycache__/tokenizer.cpython-310.pyc and b/data/__pycache__/tokenizer.cpython-310.pyc differ
 
models/__pycache__/codebooks_patterns.cpython-310.pyc CHANGED
Binary files a/models/__pycache__/codebooks_patterns.cpython-310.pyc and b/models/__pycache__/codebooks_patterns.cpython-310.pyc differ
 
models/__pycache__/voicecraft.cpython-310.pyc CHANGED
Binary files a/models/__pycache__/voicecraft.cpython-310.pyc and b/models/__pycache__/voicecraft.cpython-310.pyc differ
 
models/modules/__pycache__/__init__.cpython-310.pyc CHANGED
Binary files a/models/modules/__pycache__/__init__.cpython-310.pyc and b/models/modules/__pycache__/__init__.cpython-310.pyc differ
 
models/modules/__pycache__/activation.cpython-310.pyc CHANGED
Binary files a/models/modules/__pycache__/activation.cpython-310.pyc and b/models/modules/__pycache__/activation.cpython-310.pyc differ
 
models/modules/__pycache__/embedding.cpython-310.pyc CHANGED
Binary files a/models/modules/__pycache__/embedding.cpython-310.pyc and b/models/modules/__pycache__/embedding.cpython-310.pyc differ
 
models/modules/__pycache__/scaling.cpython-310.pyc CHANGED
Binary files a/models/modules/__pycache__/scaling.cpython-310.pyc and b/models/modules/__pycache__/scaling.cpython-310.pyc differ
 
models/modules/__pycache__/transformer.cpython-310.pyc CHANGED
Binary files a/models/modules/__pycache__/transformer.cpython-310.pyc and b/models/modules/__pycache__/transformer.cpython-310.pyc differ
 
models/modules/__pycache__/utils.cpython-310.pyc CHANGED
Binary files a/models/modules/__pycache__/utils.cpython-310.pyc and b/models/modules/__pycache__/utils.cpython-310.pyc differ
 
pretrained_models/giga830M.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2454b51575822a04d24a00f8ba78f201f916439ffa62a3c1ac0ffa5220f429e3
3
+ size 3358342977
requirements.txt CHANGED
@@ -1,9 +1,6 @@
1
- -e git+https://github.com/facebookresearch/audiocraft.git@c5157b5bf14bf83449c17ea1eeb66c19fb4bc7f0#egg=audiocraft
2
- xformers==0.0.22
3
- torchaudio==2.0.2
4
- torch==2.0.1
5
  phonemizer==3.2.1
6
- gradio==3.50.2
7
  nltk>=3.8.1
8
  openai-whisper>=20231117
9
  spaces
 
1
+ -e git+https://github.com/facebookresearch/audiocraft.git@f83babff6b5e97f75562127c4cc8122229c8f099#egg=audiocraft
 
 
 
2
  phonemizer==3.2.1
3
+ gradio
4
  nltk>=3.8.1
5
  openai-whisper>=20231117
6
  spaces