kevinwang676 commited on
Commit
974e687
1 Parent(s): 6fe5d0a

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +27 -28
app.py CHANGED
@@ -321,35 +321,11 @@ while run_server:
321
  with gr.Column():
322
  placeholder = "Enter text here."
323
  input_text = gr.Textbox(label="Input Text", lines=4, placeholder=placeholder)
 
324
  with gr.Column():
325
  seedcomponent = gr.Number(label="Seed (default -1 = Random)", precision=0, value=-1)
326
  batchcount = gr.Number(label="Batch count", precision=0, value=1)
327
- with gr.Row():
328
- with gr.Column():
329
- examples = [
330
- "Special meanings: [laughter] [laughs] [sighs] [music] [gasps] [clears throat] MAN: WOMAN:",
331
- "♪ Never gonna make you cry, never gonna say goodbye, never gonna tell a lie and hurt you ♪",
332
- "And now — a picture of a larch [laughter]",
333
- """
334
- WOMAN: I would like an oatmilk latte please.
335
- MAN: Wow, that's expensive!
336
- """,
337
- """<?xml version="1.0"?>
338
- <speak version="1.0" xmlns="http://www.w3.org/2001/10/synthesis"
339
- xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
340
- xsi:schemaLocation="http://www.w3.org/2001/10/synthesis
341
- http://www.w3.org/TR/speech-synthesis/synthesis.xsd"
342
- xml:lang="en-US">
343
- <voice name="/v2/en_speaker_9">Look at that drunk guy!</voice>
344
- <voice name="/v2/en_speaker_3">Who is he?</voice>
345
- <voice name="/v2/en_speaker_9">WOMAN: [clears throat] 10 years ago, he proposed me and I rejected him.</voice>
346
- <voice name="/v2/en_speaker_3">Oh my God [laughs] he is still celebrating</voice>
347
- </speak>"""
348
- ]
349
- examples = gr.Examples(examples=examples, inputs=input_text)
350
- with gr.Column():
351
- convert_to_ssml_button = gr.Button("Convert Input Text to SSML")
352
-
353
  with gr.Row():
354
  with gr.Column():
355
  gr.Markdown("[Voice Prompt Library](https://suno-ai.notion.site/8b8e8749ed514b0cbf3f699013548683?v=bc67cff786b04b50b3ceb756fd05f68c)")
@@ -376,7 +352,30 @@ while run_server:
376
  with gr.Row():
377
  output_audio = gr.Audio(label="Generated Audio", type="filepath")
378
 
379
- with gr.Tab("Swap Voice"):
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
380
  with gr.Row():
381
  swap_audio_filename = gr.Audio(label="Input audio.wav to swap voice", source="upload", type="filepath")
382
  with gr.Row():
@@ -387,7 +386,7 @@ while run_server:
387
  speaker_swap = gr.Dropdown(speakers_list, value=speakers_list[0], label="Voice")
388
  swap_batchcount = gr.Number(label="Batch count", precision=0, value=1)
389
  with gr.Row():
390
- swap_voice_button = gr.Button("Swap Voice")
391
  with gr.Row():
392
  output_swap = gr.Audio(label="Generated Audio", type="filepath")
393
 
 
321
  with gr.Column():
322
  placeholder = "Enter text here."
323
  input_text = gr.Textbox(label="Input Text", lines=4, placeholder=placeholder)
324
+ convert_to_ssml_button = gr.Button("Convert Input Text to SSML")
325
  with gr.Column():
326
  seedcomponent = gr.Number(label="Seed (default -1 = Random)", precision=0, value=-1)
327
  batchcount = gr.Number(label="Batch count", precision=0, value=1)
328
+
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
329
  with gr.Row():
330
  with gr.Column():
331
  gr.Markdown("[Voice Prompt Library](https://suno-ai.notion.site/8b8e8749ed514b0cbf3f699013548683?v=bc67cff786b04b50b3ceb756fd05f68c)")
 
352
  with gr.Row():
353
  output_audio = gr.Audio(label="Generated Audio", type="filepath")
354
 
355
+ with gr.Row():
356
+ examples = [
357
+ "Special meanings: [laughter] [laughs] [sighs] [music] [gasps] [clears throat] MAN: WOMAN:",
358
+ "♪ Never gonna make you cry, never gonna say goodbye, never gonna tell a lie and hurt you ♪",
359
+ "And now — a picture of a larch [laughter]",
360
+ """
361
+ WOMAN: I would like an oatmilk latte please.
362
+ MAN: Wow, that's expensive!
363
+ """,
364
+ """<?xml version="1.0"?>
365
+ <speak version="1.0" xmlns="http://www.w3.org/2001/10/synthesis"
366
+ xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
367
+ xsi:schemaLocation="http://www.w3.org/2001/10/synthesis
368
+ http://www.w3.org/TR/speech-synthesis/synthesis.xsd"
369
+ xml:lang="en-US">
370
+ <voice name="/v2/en_speaker_9">Look at that drunk guy!</voice>
371
+ <voice name="/v2/en_speaker_3">Who is he?</voice>
372
+ <voice name="/v2/en_speaker_9">WOMAN: [clears throat] 10 years ago, he proposed me and I rejected him.</voice>
373
+ <voice name="/v2/en_speaker_3">Oh my God [laughs] he is still celebrating</voice>
374
+ </speak>"""
375
+ ]
376
+ examples = gr.Examples(examples=examples, inputs=input_text)
377
+
378
+ with gr.Tab("Voice Conversion"):
379
  with gr.Row():
380
  swap_audio_filename = gr.Audio(label="Input audio.wav to swap voice", source="upload", type="filepath")
381
  with gr.Row():
 
386
  speaker_swap = gr.Dropdown(speakers_list, value=speakers_list[0], label="Voice")
387
  swap_batchcount = gr.Number(label="Batch count", precision=0, value=1)
388
  with gr.Row():
389
+ swap_voice_button = gr.Button("Voice Conversion")
390
  with gr.Row():
391
  output_swap = gr.Audio(label="Generated Audio", type="filepath")
392