haoheliu commited on
Commit
a3967e1
1 Parent(s): 3901b16

change default checkpoint

Browse files
Files changed (1) hide show
  1. app.py +6 -6
app.py CHANGED
@@ -239,7 +239,7 @@ with iface:
239
  guidance_scale = gr.Slider(0, 4, value=2.5, step=0.5, label="Guidance scale (Large => better quality and relavancy to text; Small => better diversity)")
240
  n_candidates = gr.Slider(1, 5, value=3, step=1, label="Automatic quality control. This number control the number of candidates (e.g., generate three audios and choose the best to show you). A Larger value usually lead to better quality with heavier computation")
241
  # model_name = gr.Dropdown(
242
- # ["audioldm-m-text-ft", "audioldm-s-text-ft", "audioldm-m-full","audioldm-s-full-v2", "audioldm-s-full", "audioldm-l-full"], value="audioldm-m-text-ft", label="Choose the model to use. audioldm-m-text-ft and audioldm-s-text-ft are recommanded. -s- means small, -m- means medium and -l- means large",
243
  # )
244
  ############# Output
245
  # outputs=gr.Audio(label="Output", type="numpy")
@@ -275,11 +275,11 @@ with iface:
275
  </div>
276
  ''')
277
  gr.Examples([
278
- ["A hammer is hitting a wooden surface", 5, 2.5, 45, 3, "audioldm-m-text-ft"],
279
- ["Peaceful and calming ambient music with singing bowl and other instruments.", 5, 2.5, 45, 3, "audioldm-m-text-ft"],
280
- ["A man is speaking in a small room.", 5, 2.5, 45, 3, "audioldm-m-text-ft"],
281
- ["A female is speaking followed by footstep sound", 5, 2.5, 45, 3, "audioldm-m-text-ft"],
282
- ["Wooden table tapping sound followed by water pouring sound.", 5, 2.5, 45, 3, "audioldm-m-text-ft"],
283
  ],
284
  fn=text2audio,
285
  # inputs=[textbox, duration, guidance_scale, seed, n_candidates, model_name],
 
239
  guidance_scale = gr.Slider(0, 4, value=2.5, step=0.5, label="Guidance scale (Large => better quality and relavancy to text; Small => better diversity)")
240
  n_candidates = gr.Slider(1, 5, value=3, step=1, label="Automatic quality control. This number control the number of candidates (e.g., generate three audios and choose the best to show you). A Larger value usually lead to better quality with heavier computation")
241
  # model_name = gr.Dropdown(
242
+ # ["audioldm-m-text-ft", "audioldm-s-text-ft", "audioldm-m-full","audioldm-s-full-v2", "audioldm-s-full", "audioldm-l-full"], value="audioldm-m-full", label="Choose the model to use. audioldm-m-text-ft and audioldm-s-text-ft are recommanded. -s- means small, -m- means medium and -l- means large",
243
  # )
244
  ############# Output
245
  # outputs=gr.Audio(label="Output", type="numpy")
 
275
  </div>
276
  ''')
277
  gr.Examples([
278
+ ["A hammer is hitting a wooden surface", 5, 2.5, 45, 3, "audioldm-m-full"],
279
+ ["Peaceful and calming ambient music with singing bowl and other instruments.", 5, 2.5, 45, 3, "audioldm-m-full"],
280
+ ["A man is speaking in a small room.", 5, 2.5, 45, 3, "audioldm-m-full"],
281
+ ["A female is speaking followed by footstep sound", 5, 2.5, 45, 3, "audioldm-m-full"],
282
+ ["Wooden table tapping sound followed by water pouring sound.", 5, 2.5, 45, 3, "audioldm-m-full"],
283
  ],
284
  fn=text2audio,
285
  # inputs=[textbox, duration, guidance_scale, seed, n_candidates, model_name],