rest

app.py

@@ -5,11 +5,28 @@ from io import BytesIO
 import numpy as np
 import librosa
 import tempfile
+from twilio.rest import Client
+import os
 from transformers import Qwen2AudioForConditionalGeneration, AutoProcessor
 
 processor = AutoProcessor.from_pretrained("Qwen/Qwen2-Audio-7B-Instruct")
 model = Qwen2AudioForConditionalGeneration.from_pretrained("Qwen/Qwen2-Audio-7B-Instruct", device_map="auto")
 
+account_sid = os.environ.get("TWILIO_ACCOUNT_SID")
+auth_token = os.environ.get("TWILIO_AUTH_TOKEN")
+
+if account_sid and auth_token:
+    client = Client(account_sid, auth_token)
+
+    token = client.tokens.create()
+
+    rtc_configuration = {
+        "iceServers": token.ice_servers,
+        "iceTransportPolicy": "relay",
+    }
+else:
+    rtc_configuration = None
+
 
 def transcribe(audio: tuple[int, np.ndarray], transformers_convo: list[dict], gradio_convo: list[dict]):
     segment = AudioSegment(
@@ -51,6 +68,7 @@ with gr.Blocks() as demo:
     with gr.Row():
         with gr.Column():
             audio = WebRTC(
+                rtc_configuration=rtc_configuration,
                 label="Stream",
                 mode="send",
                 modality="audio",

requirements.txt

@@ -1,2 +1,3 @@
 gradio_webrtc[vad]==0.0.11a1
-transformers@git+https://github.com/huggingface/transformers
+transformers@git+https://github.com/huggingface/transformers
+twilio