Update app.py
Browse files
app.py
CHANGED
@@ -7,7 +7,7 @@ from transformers import pipeline
|
|
7 |
device = "cuda" if torch.cuda.is_available() else "cpu"
|
8 |
|
9 |
speech_to_text = pipeline("automatic-speech-recognition", model="openai/whisper-large-v3-turbo", device=device)
|
10 |
-
text_to_speech = pipeline("text-to-speech", model="facebook/seamless-streaming", device=device)
|
11 |
|
12 |
def audio_to_audio_chatbot(audio):
|
13 |
if audio is None:
|
@@ -22,14 +22,15 @@ def audio_to_audio_chatbot(audio):
|
|
22 |
print(f"Bot: {response_text}")
|
23 |
|
24 |
# 3. Text-to-Speech
|
25 |
-
speech = text_to_speech(response_text)
|
26 |
-
return speech["audio"], response_text
|
27 |
|
28 |
if __name__ == "__main__":
|
29 |
iface = gr.Interface(
|
30 |
fn=audio_to_audio_chatbot,
|
31 |
inputs=gr.Audio(source="microphone", type="filepath"),
|
32 |
-
outputs=
|
|
|
33 |
title="Audio-zu-Audio-Chatbot (Streaming)",
|
34 |
description="Spreche in das Mikrofon und der Bot antwortet mit einer Audio-Ausgabe.",
|
35 |
live=True # Aktiviert Streaming
|
|
|
7 |
device = "cuda" if torch.cuda.is_available() else "cpu"
|
8 |
|
9 |
speech_to_text = pipeline("automatic-speech-recognition", model="openai/whisper-large-v3-turbo", device=device)
|
10 |
+
#text_to_speech = pipeline("text-to-speech", model="facebook/seamless-streaming", device=device)
|
11 |
|
12 |
def audio_to_audio_chatbot(audio):
|
13 |
if audio is None:
|
|
|
22 |
print(f"Bot: {response_text}")
|
23 |
|
24 |
# 3. Text-to-Speech
|
25 |
+
#speech = text_to_speech(response_text)
|
26 |
+
#return speech["audio"], response_text
|
27 |
|
28 |
if __name__ == "__main__":
|
29 |
iface = gr.Interface(
|
30 |
fn=audio_to_audio_chatbot,
|
31 |
inputs=gr.Audio(source="microphone", type="filepath"),
|
32 |
+
outputs= gr.Textbox(),
|
33 |
+
#outputs=[gr.Audio(), gr.Textbox()],
|
34 |
title="Audio-zu-Audio-Chatbot (Streaming)",
|
35 |
description="Spreche in das Mikrofon und der Bot antwortet mit einer Audio-Ausgabe.",
|
36 |
live=True # Aktiviert Streaming
|