Upload 6 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+M23IQT007.pdf filter=lfs diff=lfs merge=lfs -text

M23IQT007.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1db532e463a5591c3d4852d142189178c7e01e21fc75523b7b713983628d421d
+size 510689

app.py

@@ -0,0 +1,29 @@
+from fastapi import FastAPI, UploadFile, File
+import whisper
+from transformers import pipeline
+import tempfile
+
+app = FastAPI()
+
+# Load Models
+speech_model = whisper.load_model("base")
+sentiment_analyzer = pipeline("sentiment-analysis")
+
+@app.post("/analyze/")
+async def analyze(audio: UploadFile = File(...)):
+    with tempfile.NamedTemporaryFile(delete=False) as temp:
+        temp.write(await audio.read())
+        temp_path = temp.name
+
+    # Transcribe Speech
+    transcription = speech_model.transcribe(temp_path)["text"]
+
+    # Analyze Sentiment
+    sentiment = sentiment_analyzer(transcription)
+
+    return {
+        "transcription": transcription,
+        "sentiment": sentiment[0]
+    }
+
+# Run Server: uvicorn app:app --reload

gradio_ui.py

@@ -0,0 +1,18 @@
+import gradio as gr
+import requests
+
+def process_audio(audio):
+    files = {"audio": audio}
+    response = requests.post("http://127.0.0.1:8000/analyze/", files=files)
+
+    if response.status_code == 200:
+        data = response.json()
+        return data["transcription"], data["sentiment"]
+    else:
+        return "Error", "Error"
+
+gr.Interface(
+    fn=process_audio,
+    inputs="audio",
+    outputs=["text", "text"]
+).launch(share=True)

sentiment_analysis.py

@@ -0,0 +1,14 @@
+from transformers import pipeline
+
+# Load Pre-trained Sentiment Model
+sentiment_analyzer = pipeline("sentiment-analysis")
+
+def analyze_sentiment(text):
+    result = sentiment_analyzer(text)
+    return result[0]
+
+# Test
+if __name__ == "__main__":
+    text = "I am really happy with the service!"
+    sentiment = analyze_sentiment(text)
+    print("Sentiment:", sentiment)

speech_to_text.py

@@ -0,0 +1,13 @@
+import whisper
+
+# Load Whisper Model
+model = whisper.load_model("base")
+
+def transcribe_audio(audio_file):
+    result = model.transcribe(audio_file)
+    return result["text"]
+
+# Test
+if __name__ == "__main__":
+    transcript = transcribe_audio("sample_audio.wav")
+    print("Transcription:", transcript)

ui.py

@@ -0,0 +1,17 @@
+import streamlit as st
+import requests
+
+st.title("AI Voice Intelligence for Customer Support")
+
+uploaded_file = st.file_uploader("Upload an audio file", type=["wav", "mp3"])
+
+if uploaded_file:
+    files = {"audio": uploaded_file.getvalue()}
+    response = requests.post("http://127.0.0.1:8000/analyze/", files=files)
+
+    if response.status_code == 200:
+        data = response.json()
+        st.write("### Transcription:")
+        st.write(data["transcription"])
+        st.write("### Sentiment Analysis:")
+        st.write(data["sentiment"])