Spaces:
Sleeping
Sleeping
File size: 1,792 Bytes
a469909 |
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 |
import gradio as gr
import requests
import tensorflow as tf
from transformers import pipeline
# audio2text
trans = pipeline("automatic-speech-recognition", model = "facebook/wav2vec2-large-xlsr-53-spanish")
def audio2text(audio):
text = trans(audio)["text"]
return text
# text2sentiment
classifier = pipeline("text-classification", model = "pysentimiento/robertuito-sentiment-analysis")
def text2sentiment(text):
return classifier(text)[0]["label"]
# image_classification
inception_net = tf.keras.applications.MobileNetV2()
answer = requests.get("https://git.io/JJkYN")
labels = answer.text.split("\n")
def image_classification(inp):
inp = inp.reshape((-1,224,224,3))
inp = tf.keras.applications.mobilenet_v2.preprocess_input(inp)
prediction = inception_net.predict(inp).flatten()
confidences = {labels[i]: float(prediction[i]) for i in range(1000)}
return confidences
# demo
demo = gr.Blocks()
with demo:
gr.Markdown("This is the second demo with Blocks")
with gr.Tabs():
with gr.TabItem("Transcribe audio in Spanish"):
with gr.Row():
audio = gr.Audio(source="microphone", type="filepath")
transcription = gr.Textbox()
b1 = gr.Button("Transcribe")
with gr.TabItem("Sentiment analysis in Spanish"):
with gr.Row():
text = gr.Textbox()
label_sentiment = gr.Label()
b2 = gr.Button("Sentiment")
with gr.TabItem("Image classification"):
with gr.Row():
image=gr.Image(shape=(224,224))
label_image=gr.Label(num_top_classes=3)
b3 = gr.Button("Classify")
b1.click(audio2text, inputs = audio, outputs=transcription)
b2.click(text2sentiment, inputs=text, outputs=label_sentiment)
b3.click(image_classification, inputs=image, outputs=label_image)
demo.launch() |