import gradio as gr
from zeroshot import (
process,
WORD_SCORE_DEFAULT_IF_LM,
WORD_SCORE_DEFAULT_IF_NOLM,
LM_SCORE_DEFAULT,
)
with gr.Blocks(css="style.css") as demo:
gr.Markdown(
"
MMS Zero-shot ASR Demo. See our arXiV paper for model details.
"
)
gr.HTML(
"""The demo works on input audio in any language, as long as you provide a list of words or sentences for that language and an optional n-gram language model (even a simple 1-gram model will work!) to help with accuracy.
We recommend having a minimum of 10000 sentences in the textfile to acheive a good performance."""
)
with gr.Row():
with gr.Column():
audio = gr.Audio(label="Audio Input\n(use microphone or upload a file)")
with gr.Row():
words_file = gr.File(label="Text Data")
lm_file = gr.File(label="Language Model\n(optional)")
with gr.Accordion("Advanced Settings", open=False):
gr.Markdown(
"The following parameters are used for beam-search decoding. Use the default values if you are not sure."
)
with gr.Row():
with gr.Column():
wscore_usedefault = gr.Checkbox(
label="Use Default Word Insertion Score", value=True
)
wscore = gr.Slider(
minimum=-10.0,
maximum=10.0,
value=WORD_SCORE_DEFAULT_IF_LM,
step=0.1,
interactive=False,
label="Word Insertion Score",
)
with gr.Column():
lmscore_usedefault = gr.Checkbox(
label="Use Default Language Model Score", value=True
)
lmscore = gr.Slider(
minimum=-10.0,
maximum=10.0,
value=LM_SCORE_DEFAULT,
step=0.1,
interactive=False,
label="Language Model Score",
)
with gr.Column():
autolm = gr.Checkbox(
label="Automatically create Unigram LM from text data",
value=True,
)
btn = gr.Button("Submit", elem_id="submit")
@gr.on(
inputs=[wscore_usedefault, lmscore_usedefault, lm_file, autolm],
outputs=[wscore, lmscore],
)
def update_slider(ws, ls, lm, alm):
ws_slider = gr.Slider(
minimum=-10.0,
maximum=10.0,
value=LM_SCORE_DEFAULT if (lm is not None or alm) else 0,
step=0.1,
interactive=not ws,
label="Word Insertion Score",
)
ls_slider = gr.Slider(
minimum=-10.0,
maximum=10.0,
value=WORD_SCORE_DEFAULT_IF_NOLM
if (lm is None and not alm)
else WORD_SCORE_DEFAULT_IF_LM,
step=0.1,
interactive=not ls,
label="Language Model Score",
)
return ws_slider, ls_slider
with gr.Column():
text = gr.Textbox(label="Transcript")
with gr.Accordion("Logs", open=False):
logs = gr.Textbox(show_label=False)
# hack
reference = gr.Textbox(label="Reference Transcript", visible=False)
btn.click(
process,
inputs=[
audio,
words_file,
lm_file,
wscore,
lmscore,
wscore_usedefault,
lmscore_usedefault,
autolm,
reference,
],
outputs=[text, logs],
)
# Examples
gr.Examples(
examples=[
# ["upload/english/english.mp3", "upload/english/c4_25k_sentences.txt"],
[
"upload/english/english.mp3",
"upload/english/c4_10k_sentences.txt",
" This is going to look at the code that we have in our configuration that we've already exported and compare it to our database, and we want to import",
],
[
"upload/english/english.mp3",
"upload/english/c4_5k_sentences.txt",
" This is going to look at the code that we have in our configuration that we've already exported and compare it to our database, and we want to import",
],
[
"upload/english/english.mp3",
"upload/english/gutenberg_27045.txt",
" This is going to look at the code that we have in our configuration that we've already exported and compare it to our database, and we want to import",
],
],
inputs=[audio, words_file, reference],
label="English",
)
gr.Examples(
examples=[
# ["upload/english/english.mp3", "upload/english/c4_25k_sentences.txt"],
[
"upload/ligurian/ligurian_1.mp3",
"upload/ligurian/zenamt_10k_sentences.txt",
"I mæ colleghi m’an domandou d’aggiuttâli à fâ unna preuva co-o zeneise pe vedde s’o fonçioña.",
],
[
"upload/ligurian/ligurian_2.mp3",
"upload/ligurian/zenamt_10k_sentences.txt",
"Staseia vaggo à çenâ con mæ moggê e doî amixi che de chì à quarche settemaña faian stramuo feua stato.",
],
[
"upload/ligurian/ligurian_3.mp3",
"upload/ligurian/zenamt_5k_sentences.txt",
"Pe inandiâ o pesto ghe veu o baxaicò, i pigneu, l’euio, o formaggio, l’aggio e a sâ.",
],
],
inputs=[audio, words_file, reference],
label="Ligurian",
)
demo.launch()