Spaces:
Running
on
Zero
Running
on
Zero
Update app.py
Browse files
app.py
CHANGED
|
@@ -545,18 +545,21 @@ def update_speed(new_speed):
|
|
| 545 |
|
| 546 |
with gr.Blocks() as app_credits:
|
| 547 |
gr.Markdown("""
|
| 548 |
-
# Credits
|
|
|
|
|
|
|
|
|
|
|
|
|
| 549 |
|
| 550 |
-
* [mrfakename](https://github.com/fakerybakery) for the original [online demo](https://huggingface.co/spaces/mrfakename/E2-F5-TTS)
|
| 551 |
-
* [RootingInLoad](https://github.com/RootingInLoad) for the podcast generation
|
| 552 |
-
* [jpgallegoar](https://github.com/jpgallegoar) for multiple speech-type generation
|
| 553 |
-
""")
|
| 554 |
with gr.Blocks() as app_tts:
|
| 555 |
gr.Markdown("# Batched TTS")
|
| 556 |
ref_audio_input = gr.Audio(label="Reference Audio", type="filepath")
|
| 557 |
gen_text_input = gr.Textbox(label="Text to Generate", lines=10)
|
| 558 |
model_choice = gr.Radio(
|
| 559 |
-
choices=["English","Polish","Deutsch"], label="Choose TTS Model", value="English"
|
|
|
|
|
|
|
|
|
|
| 560 |
)
|
| 561 |
generate_btn = gr.Button("Synthesize", variant="primary")
|
| 562 |
with gr.Accordion("Advanced Settings", open=False):
|
|
@@ -574,7 +577,7 @@ with gr.Blocks() as app_tts:
|
|
| 574 |
label="Speed",
|
| 575 |
minimum=0.3,
|
| 576 |
maximum=2.0,
|
| 577 |
-
value=speed
|
| 578 |
step=0.1,
|
| 579 |
info="Adjust the speed of the audio.",
|
| 580 |
)
|
|
@@ -600,11 +603,10 @@ with gr.Blocks() as app_tts:
|
|
| 600 |
model_choice,
|
| 601 |
remove_silence,
|
| 602 |
cross_fade_duration_slider,
|
| 603 |
-
|
| 604 |
],
|
| 605 |
outputs=[audio_output, spectrogram_output],
|
| 606 |
)
|
| 607 |
-
|
| 608 |
|
| 609 |
def parse_emotional_text(gen_text):
|
| 610 |
# Pattern to find (Emotion)
|
|
|
|
| 545 |
|
| 546 |
with gr.Blocks() as app_credits:
|
| 547 |
gr.Markdown("""
|
| 548 |
+
# Credits
|
| 549 |
+
* [mrfakename](https://github.com/fakerybakery) for the original [online demo](https://huggingface.co/spaces/mrfakename/E2-F5-TTS)
|
| 550 |
+
* [RootingInLoad](https://github.com/RootingInLoad) for the podcast generation
|
| 551 |
+
* [jpgallegoar](https://github.com/jpgallegoar) for multiple speech-type generation
|
| 552 |
+
""")
|
| 553 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 554 |
with gr.Blocks() as app_tts:
|
| 555 |
gr.Markdown("# Batched TTS")
|
| 556 |
ref_audio_input = gr.Audio(label="Reference Audio", type="filepath")
|
| 557 |
gen_text_input = gr.Textbox(label="Text to Generate", lines=10)
|
| 558 |
model_choice = gr.Radio(
|
| 559 |
+
choices=["English", "Polish", "Deutsch"], label="Choose TTS Model", value="English"
|
| 560 |
+
)
|
| 561 |
+
language_choice = gr.Dropdown(
|
| 562 |
+
choices=["pl", "de", "en-us", "en-gb", "uk", "ru"], label="Choose Language", value="en-gb"
|
| 563 |
)
|
| 564 |
generate_btn = gr.Button("Synthesize", variant="primary")
|
| 565 |
with gr.Accordion("Advanced Settings", open=False):
|
|
|
|
| 577 |
label="Speed",
|
| 578 |
minimum=0.3,
|
| 579 |
maximum=2.0,
|
| 580 |
+
value=1.0, # Assuming a default speed value
|
| 581 |
step=0.1,
|
| 582 |
info="Adjust the speed of the audio.",
|
| 583 |
)
|
|
|
|
| 603 |
model_choice,
|
| 604 |
remove_silence,
|
| 605 |
cross_fade_duration_slider,
|
| 606 |
+
language_choice,
|
| 607 |
],
|
| 608 |
outputs=[audio_output, spectrogram_output],
|
| 609 |
)
|
|
|
|
| 610 |
|
| 611 |
def parse_emotional_text(gen_text):
|
| 612 |
# Pattern to find (Emotion)
|