OpenSound commited on
Commit
468a602
·
verified ·
1 Parent(s): 4d72af4

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +12 -6
app.py CHANGED
@@ -264,27 +264,33 @@ css = """
264
  with gr.Blocks(css=css, theme=gr.themes.Soft()) as demo:
265
  with gr.Column(elem_id="col-container"):
266
  gr.Markdown("""
267
- # 🎸 SoloSpeech: Enhancing Intelligibility and Quality in Target Speech Extraction through a Cascaded Generative Pipeline
268
  Extract the target voice from mixture speech given an enrollment speech.
269
 
270
- Learn more about **SoloSpeech** on the [SoloSpeech Repo](https://github.com/WangHelin1997/SoloSpeech/).
 
 
 
271
  """)
272
 
273
  with gr.Tab("Target Speech Extraction"):
274
  with gr.Row():
275
  mixture_input = gr.Audio(label="Upload Mixture Audio", type="filepath", value="test2.wav")
 
 
276
  enroll_input = gr.Audio(label="Upload Enrollment Audio", type="filepath", value="test2_enroll.wav")
 
 
277
 
278
  with gr.Row():
 
 
 
279
  demo_selector = gr.Dropdown(
280
  label="Select Test Demo",
281
  choices=[name for name, _, _ in demo_audio_files],
282
  value="Test Demo 2"
283
  )
284
- extract_button = gr.Button("Extract", scale=1)
285
-
286
- with gr.Row():
287
- result = gr.Audio(label="Extracted Speech", type="numpy")
288
 
289
  # Update audio inputs when selecting from dropdown
290
  def update_audio_inputs(choice):
 
264
  with gr.Blocks(css=css, theme=gr.themes.Soft()) as demo:
265
  with gr.Column(elem_id="col-container"):
266
  gr.Markdown("""
267
+ # SoloSpeech: Enhancing Intelligibility and Quality in Target Speech Extraction through a Cascaded Generative Pipeline
268
  Extract the target voice from mixture speech given an enrollment speech.
269
 
270
+ Learn more about 🎯**SoloSpeech** on the [SoloSpeech Repo](https://github.com/WangHelin1997/SoloSpeech/).
271
+
272
+ Tip: Tip: To extract sound effects or music from audio, try using [SoloAudio](https://huggingface.co/spaces/OpenSound/SoloAudio).
273
+
274
  """)
275
 
276
  with gr.Tab("Target Speech Extraction"):
277
  with gr.Row():
278
  mixture_input = gr.Audio(label="Upload Mixture Audio", type="filepath", value="test2.wav")
279
+
280
+ with gr.Row(equal_height=True):
281
  enroll_input = gr.Audio(label="Upload Enrollment Audio", type="filepath", value="test2_enroll.wav")
282
+ extract_button = gr.Button("Extract", scale=1)
283
+ # extract_button = gr.Button("Extract", scale=1)
284
 
285
  with gr.Row():
286
+ result = gr.Audio(label="Extracted Speech", type="numpy")
287
+
288
+ with gr.Row(equal_height=True):
289
  demo_selector = gr.Dropdown(
290
  label="Select Test Demo",
291
  choices=[name for name, _, _ in demo_audio_files],
292
  value="Test Demo 2"
293
  )
 
 
 
 
294
 
295
  # Update audio inputs when selecting from dropdown
296
  def update_audio_inputs(choice):