Update app.py

app.py

@@ -2,6 +2,7 @@ import os
 import numpy as np
 import gradio as gr
 from gradio.mix import Series
+from transformers import pipeline
 
 path_to_L_model = str(os.environ['path_to_L_model'])
 read_token      = str(os.environ['read_token'])
@@ -9,17 +10,46 @@ read_token      = str(os.environ['read_token'])
 description = "Talk to Breud!"
 title       = "Breud (BERT + Freud)"
 
-wisper = gr.Interface.load("models/openai/whisper-base")
+# wisper = gr.Interface.load("models/openai/whisper-base")
 
-interface_model_L = gr.Interface.load(
-            name=path_to_L_model,
-            api_key=read_token,
-)
+# interface_model_L = gr.Interface.load(
+#             name=path_to_L_model,
+#             api_key=read_token,
+# )
 
-Series( 
-    wisper, 
-    interface_model_L,
-    description = description,
-    title = title,
-    inputs = gr.Audio(source="microphone"),
-).launch()
+# Series( 
+#     wisper, 
+#     interface_model_L,
+#     description = description,
+#     title = title,
+#     inputs = gr.Audio(source="microphone"),
+# ).launch()
+
+
+asr = pipeline("automatic-speech-recognition", "models/openai/whisper-base")
+classifier = pipeline("text-classification", path_to_L_model, api_token=read_token)
+
+
+def speech_to_text(speech):
+    text = asr(speech)["text"]
+    return text
+
+
+def text_to_sentiment(text):
+    return classifier(text)[0]["label"]
+
+
+demo = gr.Blocks()
+
+with demo:
+    audio_file = gr.Audio(source="microphone")
+    text = gr.Textbox()
+    label = gr.Label()
+
+    b1 = gr.Button("Recognize Speech")
+    b2 = gr.Button("Classify Sentiment")
+
+    b1.click(speech_to_text, inputs=audio_file, outputs=text)
+    b2.click(text_to_sentiment, inputs=text, outputs=label)
+
+demo.launch()