import gradio as gr | |
import subprocess | |
predefined_texts = ["Example text 1", "Example text 2", "Example text 3"] | |
def synthesize_speech(text, speaker_id): | |
command = f"python3 synthesize.py --text '{text}' --bert_embed 1 --speaker_id {speaker_id} --restore_step 900000 --mode single -p config/EmoV_DB/preprocess.yaml -m config/EmoV_DB/model.yaml -t config/EmoV_DB/train.yaml" | |
output = subprocess.check_output(command, shell=True) | |
# Replace this with the path of the generated audio file | |
audio_file = 'output_file_path' | |
return audio_file | |
iface = gr.Interface(fn=synthesize_speech, | |
inputs=[gr.inputs.Dropdown(choices=predefined_texts, label="Select a text"), | |
gr.inputs.Slider(minimum=0, maximum=10, step=1, default=0, label="Speaker ID")], | |
outputs=gr.outputs.Audio(type="file"), | |
title="Text-to-Speech Demo") | |
iface.launch() | |