sanchit-gandhi commited on
Commit
80ca0fc
·
1 Parent(s): f418560

bump streaming default

Browse files
Files changed (1) hide show
  1. app.py +10 -10
app.py CHANGED
@@ -36,22 +36,22 @@ examples = [
36
  [
37
  "Remember - this is only the first iteration of the model! To improve the prosody and naturalness of the speech further, we're scaling up the amount of training data by a factor of five times.",
38
  "A male speaker with a low-pitched voice delivering his words at a fast pace in a small, confined space with a very clear audio and an animated tone.",
39
- 2.5,
40
  ],
41
  [
42
  "'This is the best time of my life, Bartley,' she said happily.",
43
  "A female speaker with a slightly low-pitched, quite monotone voice delivers her words at a slightly faster-than-average pace in a confined space with very clear audio.",
44
- 2.5,
45
  ],
46
  [
47
  "Montrose also, after having experienced still more variety of good and bad fortune, threw down his arms, and retired out of the kingdom.",
48
  "A male speaker with a slightly high-pitched voice delivering his words at a slightly slow pace in a small, confined space with a touch of background noise and a quite monotone tone.",
49
- 2.5,
50
  ],
51
  [
52
  "Montrose also, after having experienced still more variety of good and bad fortune, threw down his arms, and retired out of the kingdom.",
53
  "A male speaker with a low-pitched voice delivers his words at a fast pace and an animated tone, in a very spacious environment, accompanied by noticeable background noise.",
54
- 2.5,
55
  ],
56
  ]
57
 
@@ -59,22 +59,22 @@ jenny_examples = [
59
  [
60
  "Remember, this is only the first iteration of the model! To improve the prosody and naturalness of the speech further, we're scaling up the amount of training data by a factor of five times.",
61
  "Jenny speaks at an average pace with a slightly animated delivery in a very confined sounding environment with clear audio quality.",
62
- 2.5,
63
  ],
64
  [
65
  "'This is the best time of my life, Bartley,' she said happily.",
66
  "Jenny speaks in quite a monotone voice at a slightly faster-than-average pace in a confined space with very clear audio.",
67
- 2.5,
68
  ],
69
  [
70
  "Montrose also, after having experienced still more variety of good and bad fortune, threw down his arms, and retired out of the kingdom.",
71
  "Jenny delivers her words at a slightly slow pace in a small, confined space with a touch of background noise and a quite monotone tone.",
72
- 2.5,
73
  ],
74
  [
75
  "Montrose also, after having experienced still more variety of good and bad fortune, threw down his arms, and retired out of the kingdom.",
76
  "Jenny delivers her words at a fast pace and an animated tone, in a very spacious environment, accompanied by noticeable background noise.",
77
- 2.5,
78
  ],
79
  ]
80
 
@@ -338,7 +338,7 @@ with gr.Blocks(css=css) as block:
338
  with gr.Column():
339
  input_text = gr.Textbox(label="Input Text", lines=2, value=default_text, elem_id="input_text")
340
  description = gr.Textbox(label="Description", lines=2, value="", elem_id="input_description")
341
- play_seconds = gr.Slider(0.5, 5.0, value=2.5, step=0.5, label="Streaming interval in seconds", info="Lower = shorter chunks, lower latency, more codec steps")
342
  run_button = gr.Button("Generate Audio", variant="primary")
343
  with gr.Column():
344
  audio_out = gr.Audio(label="Parler-TTS generation", type="numpy", elem_id="audio_out", streaming=True, autoplay=True)
@@ -353,7 +353,7 @@ with gr.Blocks(css=css) as block:
353
  with gr.Column():
354
  input_text = gr.Textbox(label="Input Text", lines=2, value=jenny_examples[0][0], elem_id="input_text")
355
  description = gr.Textbox(label="Description", lines=2, value=jenny_examples[0][1], elem_id="input_description")
356
- play_seconds = gr.Slider(2.5, 5.0, value=jenny_examples[0][2], step=0.5, label="Streaming interval in seconds", info="Lower = shorter chunks, lower latency, more codec steps")
357
  run_button = gr.Button("Generate Audio", variant="primary")
358
  with gr.Column():
359
  audio_out = gr.Audio(label="Parler-TTS generation", type="numpy", elem_id="audio_out", streaming=True, autoplay=True)
 
36
  [
37
  "Remember - this is only the first iteration of the model! To improve the prosody and naturalness of the speech further, we're scaling up the amount of training data by a factor of five times.",
38
  "A male speaker with a low-pitched voice delivering his words at a fast pace in a small, confined space with a very clear audio and an animated tone.",
39
+ 3.0,
40
  ],
41
  [
42
  "'This is the best time of my life, Bartley,' she said happily.",
43
  "A female speaker with a slightly low-pitched, quite monotone voice delivers her words at a slightly faster-than-average pace in a confined space with very clear audio.",
44
+ 3.0,
45
  ],
46
  [
47
  "Montrose also, after having experienced still more variety of good and bad fortune, threw down his arms, and retired out of the kingdom.",
48
  "A male speaker with a slightly high-pitched voice delivering his words at a slightly slow pace in a small, confined space with a touch of background noise and a quite monotone tone.",
49
+ 3.0,
50
  ],
51
  [
52
  "Montrose also, after having experienced still more variety of good and bad fortune, threw down his arms, and retired out of the kingdom.",
53
  "A male speaker with a low-pitched voice delivers his words at a fast pace and an animated tone, in a very spacious environment, accompanied by noticeable background noise.",
54
+ 3.0,
55
  ],
56
  ]
57
 
 
59
  [
60
  "Remember, this is only the first iteration of the model! To improve the prosody and naturalness of the speech further, we're scaling up the amount of training data by a factor of five times.",
61
  "Jenny speaks at an average pace with a slightly animated delivery in a very confined sounding environment with clear audio quality.",
62
+ 3.0,
63
  ],
64
  [
65
  "'This is the best time of my life, Bartley,' she said happily.",
66
  "Jenny speaks in quite a monotone voice at a slightly faster-than-average pace in a confined space with very clear audio.",
67
+ 3.0,
68
  ],
69
  [
70
  "Montrose also, after having experienced still more variety of good and bad fortune, threw down his arms, and retired out of the kingdom.",
71
  "Jenny delivers her words at a slightly slow pace in a small, confined space with a touch of background noise and a quite monotone tone.",
72
+ 3.0,
73
  ],
74
  [
75
  "Montrose also, after having experienced still more variety of good and bad fortune, threw down his arms, and retired out of the kingdom.",
76
  "Jenny delivers her words at a fast pace and an animated tone, in a very spacious environment, accompanied by noticeable background noise.",
77
+ 3.0,
78
  ],
79
  ]
80
 
 
338
  with gr.Column():
339
  input_text = gr.Textbox(label="Input Text", lines=2, value=default_text, elem_id="input_text")
340
  description = gr.Textbox(label="Description", lines=2, value="", elem_id="input_description")
341
+ play_seconds = gr.Slider(3.0, 5.0, value=3.0, step=0.5, label="Streaming interval in seconds", info="Lower = shorter chunks, lower latency, more codec steps")
342
  run_button = gr.Button("Generate Audio", variant="primary")
343
  with gr.Column():
344
  audio_out = gr.Audio(label="Parler-TTS generation", type="numpy", elem_id="audio_out", streaming=True, autoplay=True)
 
353
  with gr.Column():
354
  input_text = gr.Textbox(label="Input Text", lines=2, value=jenny_examples[0][0], elem_id="input_text")
355
  description = gr.Textbox(label="Description", lines=2, value=jenny_examples[0][1], elem_id="input_description")
356
+ play_seconds = gr.Slider(3.0, 5.0, value=jenny_examples[0][2], step=0.5, label="Streaming interval in seconds", info="Lower = shorter chunks, lower latency, more codec steps")
357
  run_button = gr.Button("Generate Audio", variant="primary")
358
  with gr.Column():
359
  audio_out = gr.Audio(label="Parler-TTS generation", type="numpy", elem_id="audio_out", streaming=True, autoplay=True)