Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
|
@@ -1,43 +1,22 @@
|
|
| 1 |
import gradio as gr
|
| 2 |
from transformers import pipeline
|
| 3 |
-
|
| 4 |
-
import IPython.display as ipd
|
| 5 |
|
| 6 |
-
|
| 7 |
-
|
| 8 |
-
# texto to audio
|
| 9 |
|
| 10 |
-
|
| 11 |
-
|
| 12 |
-
|
| 13 |
-
|
| 14 |
|
| 15 |
-
|
| 16 |
-
|
| 17 |
-
|
| 18 |
-
|
| 19 |
-
|
| 20 |
-
|
| 21 |
-
|
| 22 |
-
|
| 23 |
-
def image_to_audio(input_image):
|
| 24 |
-
# Convertir la imagen a texto
|
| 25 |
-
text_output = image_to_texto(input_image)[0]['label']
|
| 26 |
-
print('text_output is :'+text_output)
|
| 27 |
-
# Generar audio a partir del texto
|
| 28 |
-
audio_output = text_to_audio_model(text_output)[0]['audio']
|
| 29 |
-
print('audio_output is :'+audio_output)
|
| 30 |
-
return audio_output
|
| 31 |
-
|
| 32 |
-
# Interfaz Gradio
|
| 33 |
-
iface = gr.Interface(
|
| 34 |
-
fn=image_to_audio,
|
| 35 |
-
inputs=gr.Image(type='pil'),
|
| 36 |
-
outputs=[gr.Textbox(), gr.Audio()],
|
| 37 |
-
live=True,
|
| 38 |
-
interpretation="default",
|
| 39 |
-
capture_session=True
|
| 40 |
-
)
|
| 41 |
|
| 42 |
-
|
| 43 |
-
iface.launch()
|
|
|
|
| 1 |
import gradio as gr
|
| 2 |
from transformers import pipeline
|
| 3 |
+
import speech_recognition as sr
|
|
|
|
| 4 |
|
| 5 |
+
def transcribe_speech():
|
| 6 |
+
r = sr.Recognizer()
|
|
|
|
| 7 |
|
| 8 |
+
# Record Audio
|
| 9 |
+
with sr.Microphone() as source:
|
| 10 |
+
print("Habla ahora:")
|
| 11 |
+
audio = r.listen(source)
|
| 12 |
|
| 13 |
+
# Speech recognition using Google Speech Recognition
|
| 14 |
+
try:
|
| 15 |
+
text = r.recognize_google(audio, language='es-ES')
|
| 16 |
+
print("Creo que dijiste: " + text)
|
| 17 |
+
except sr.UnknownValueError:
|
| 18 |
+
print("Google Speech Recognition no pudo entender el audio")
|
| 19 |
+
except sr.RequestError as e:
|
| 20 |
+
print("No se pudo solicitar resultados del servicio de Google Speech Recognition; {0}".format(e))
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
|
| 22 |
+
transcribe_speech()
|
|
|