Spaces:
Running
Running
File size: 1,798 Bytes
42a53f6 65a2eb1 42a53f6 65a2eb1 42a53f6 65a2eb1 42a53f6 65a2eb1 42a53f6 4db2518 65a2eb1 15d3e5b 42a53f6 65a2eb1 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 |
import gradio as gr
from transformers import AutoProcessor, BarkModel
import scipy
############################
### Variable Declaration ###
############################
# -- UI Variables
ui_input_voice_preseter=gr.Dropdown(
["v2/en_speaker_0","v2/en_speaker_9"], label="Voice Presenter"
)
ui_input_filename=gr.Textbox(label="Input WAV Filename")
ui_input_text=gr.Textbox(lines=22,label="Input Text")
ui_output=gr.Audio(label="Output")
# -- Model Variables
processor = AutoProcessor.from_pretrained("suno/bark")
model = BarkModel.from_pretrained("suno/bark")
############################
### Processing Functions ###
############################
# -- On Click of Submit Button in UI
def submit(voice_preseter, filename, input_text):
print("Hello World")
inputs = processor(input_text, voice_preset=voice_preseter)
audio_array = model.generate(**inputs)
audio_array = audio_array.cpu().numpy().squeeze()
sample_rate = model.generation_config.sample_rate
scipy.io.wavfile.write(filename, rate=sample_rate, data=audio_array)
retun gr.Audio(source=[os.path.join(os.path.dirname(__file__),filename])
############################
###### Main Program ########
############################
ui_input_filename = "Hello uh ... [clears throat], \
Bark is a transformer-based text-to-speech model proposed by Suno AI. \
This voice is auto generated"
# -- Start of Program - Main
def main():
demo = gr.Interface(
fn=submit,
inputs=[ui_input_voice_preseter,ui_input_filename,ui_input_text],
outputs=ui_output,
allow_flagging="never"
)
demo.queue().launch()
# -- Calling Main Function
if __name__ == '__main__':
main() |