Spaces:
Running
Running
File size: 2,706 Bytes
d079ec5 557f37f 86bc5ce 557f37f 86bc5ce 557f37f 86bc5ce 557f37f 86bc5ce d079ec5 557f37f d079ec5 557f37f 86bc5ce 557f37f 86bf20d 86bc5ce 557f37f 86bc5ce d079ec5 557f37f d079ec5 557f37f |
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 63 64 65 66 67 68 69 70 71 72 |
import gradio as gr
from transformers import pipeline
DEFAULT_MODEL = "ginic/data_seed_bs64_4_wav2vec2-large-xlsr-53-buckeye-ipa"
VALID_MODELS = [
"ctaguchi/wav2vec2-large-xlsr-japlmthufielta-ipa-plus-2000",
"ginic/data_seed_bs64_1_wav2vec2-large-xlsr-53-buckeye-ipa",
"ginic/data_seed_bs64_2_wav2vec2-large-xlsr-53-buckeye-ipa",
"ginic/data_seed_bs64_3_wav2vec2-large-xlsr-53-buckeye-ipa",
"ginic/data_seed_bs64_4_wav2vec2-large-xlsr-53-buckeye-ipa",
"ginic/gender_split_30_female_1_wav2vec2-large-xlsr-53-buckeye-ipa",
"ginic/gender_split_30_female_2_wav2vec2-large-xlsr-53-buckeye-ipa",
"ginic/gender_split_30_female_3_wav2vec2-large-xlsr-53-buckeye-ipa",
"ginic/gender_split_30_female_4_wav2vec2-large-xlsr-53-buckeye-ipa",
"ginic/gender_split_30_female_5_wav2vec2-large-xlsr-53-buckeye-ipa",
"ginic/gender_split_70_female_1_wav2vec2-large-xlsr-53-buckeye-ipa",
"ginic/gender_split_70_female_2_wav2vec2-large-xlsr-53-buckeye-ipa",
"ginic/gender_split_70_female_3_wav2vec2-large-xlsr-53-buckeye-ipa",
"ginic/gender_split_70_female_4_wav2vec2-large-xlsr-53-buckeye-ipa",
"ginic/gender_split_70_female_5_wav2vec2-large-xlsr-53-buckeye-ipa",
]
def load_model_and_predict(model_name, audio_in, model_state):
if model_state["model_name"] != model_name:
model_state = {
"loaded_model": pipeline(
task="automatic-speech-recognition", model=model_name
),
"model_name": model_name,
}
return model_state["loaded_model"](audio_in)["text"], model_state
def launch_demo():
initial_model = {
"loaded_model": pipeline(
task="automatic-speech-recognition", model=DEFAULT_MODEL
),
"model_name": DEFAULT_MODEL,
}
demo = gr.Interface(
fn=load_model_and_predict,
inputs=[
gr.Dropdown(
VALID_MODELS,
value=DEFAULT_MODEL,
label="IPA transcription ASR model",
info="Select the model to use for prediction.",
),
gr.Audio(type="filepath"),
gr.State(
value=initial_model
), # Store the name of the currently loaded model
],
outputs=[gr.Textbox(label="Predicted IPA transcription"), gr.State()],
allow_flagging="never",
title="Automatic International Phonetic Alphabet Transcription",
description="This demo allows you to experiment with producing phonetic transcriptions of uploaded or recorded audio using a selected automatic speech recognition (ASR) model.",
)
demo.launch()
if __name__ == "__main__":
launch_demo()
|