Spaces:
Sleeping
Sleeping
Create app.py
Browse files
app.py
ADDED
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import gradio as gr
|
2 |
+
from transformers import pipeline
|
3 |
+
|
4 |
+
|
5 |
+
speech_to_text = pipeline("automatic-speech-recognition", model="openai/whisper-large-v3")
|
6 |
+
text_generation = pipeline("text-generation", model="NousResearch/Hermes-2-Pro-Llama-3-8B")
|
7 |
+
text_to_speech = pipeline("text-to-speech", model="kakao-enterprise/vits-ljs")
|
8 |
+
|
9 |
+
def alexa(audio):
|
10 |
+
text = speech_to_text(audio)["text"]
|
11 |
+
generate = text_generation(text, max_length=60)[0]["generated_text"]
|
12 |
+
speech = text_to_speech(generate, lang="en", num_of_speakers = 2)["speech"]
|
13 |
+
return speech
|
14 |
+
|
15 |
+
gr.Interface.from_pipeline(
|
16 |
+
fn = alexa,
|
17 |
+
inputs = [gr.inputs.Audio(source="microphone", type="filepath")],
|
18 |
+
outputs = [gr.outputs.Audio()], live=True).launch()
|