Spaces:
Running
Running
File size: 1,550 Bytes
20aa839 3a18b3b bef8623 660776b 20aa839 3a18b3b 20aa839 cafc4cf 3a18b3b 7bc4048 ed17acd 3a18b3b 1dfec92 20aa839 9510f4a 20aa839 1dfec92 20aa839 bef8623 1dfec92 7b99c0e ed17acd b9ff9e2 bef8623 30e5da4 bef8623 9510f4a bef8623 ed17acd bef8623 20aa839 bef8623 20aa839 7bc4048 20aa839 |
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 57 58 59 60 61 62 |
import gradio as gr
import asr
import tts
import util
mms_transcribe = gr.Interface(
fn=asr.transcribe,
inputs=[
gr.Audio(),
gr.Dropdown(
choices=[model for model in asr.models_info],
label="Select a Model for ASR",
value="ixxan/wav2vec2-large-mms-1b-uyghur-latin",
interactive=True
),
],
outputs=[
gr.Textbox(label="Uyghur Arabic Transcription"),
gr.Textbox(label="Uyghur Latin Transcription"),
],
#examples=util.asr_examples,
title="Speech-to-text",
description=(
"Transcribe Uyghur speech audio from a microphone or input file."
),
allow_flagging="never",
)
mms_synthesize = gr.Interface(
fn=tts.synthesize,
inputs=[
gr.Text(label="Input text"),
gr.Dropdown(
choices=[model for model in tts.models_info],
label="Select a Model for TTS",
value="Meta-MMS",
interactive=True
)
],
outputs=[
gr.Audio(label="Generated Audio"),
],
#examples=util.tts_examples,
title="Text-to-speech",
description=(
"Generate audio from input Uyghur text."
),
allow_flagging="never",
)
tabbed_interface = gr.TabbedInterface(
[mms_transcribe, mms_synthesize],
["Speech-to-text", "Text-to-speech"],
)
with gr.Blocks() as demo:
gr.Markdown("Comparision of STT and TTS models for Uyghur language.")
tabbed_interface.render()
if __name__ == "__main__":
demo.queue()
demo.launch() |