updated faster whisper model

.idea/.gitignore

@@ -0,0 +1,8 @@
+# Default ignored files
+/shelf/
+/workspace.xml
+# Editor-based HTTP Client requests
+/httpRequests/
+# Datasource local storage ignored files
+/dataSources/
+/dataSources.local.xml

.idea/ai-interviewer-demo.iml

@@ -0,0 +1,14 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$">
+      <excludeFolder url="file://$MODULE_DIR$/.venv" />
+    </content>
+    <orderEntry type="inheritedJdk" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+  <component name="PyDocumentationSettings">
+    <option name="format" value="PLAIN" />
+    <option name="myDocStringFormat" value="Plain" />
+  </component>
+</module>

.idea/inspectionProfiles/Project_Default.xml

@@ -0,0 +1,25 @@
+<component name="InspectionProjectProfileManager">
+  <profile version="1.0">
+    <option name="myName" value="Project Default" />
+    <inspection_tool class="Eslint" enabled="true" level="WARNING" enabled_by_default="true" />
+    <inspection_tool class="PyPackageRequirementsInspection" enabled="true" level="WARNING" enabled_by_default="true">
+      <option name="ignoredPackages">
+        <value>
+          <list size="11">
+            <item index="0" class="java.lang.String" itemvalue="scipy" />
+            <item index="1" class="java.lang.String" itemvalue="scikit-learn" />
+            <item index="2" class="java.lang.String" itemvalue="opencv-python" />
+            <item index="3" class="java.lang.String" itemvalue="pip" />
+            <item index="4" class="java.lang.String" itemvalue="numpy" />
+            <item index="5" class="java.lang.String" itemvalue="datasets" />
+            <item index="6" class="java.lang.String" itemvalue="evaluate" />
+            <item index="7" class="java.lang.String" itemvalue="fuzzywuzzy" />
+            <item index="8" class="java.lang.String" itemvalue="ragas" />
+            <item index="9" class="java.lang.String" itemvalue="TTS" />
+            <item index="10" class="java.lang.String" itemvalue="textract" />
+          </list>
+        </value>
+      </option>
+    </inspection_tool>
+  </profile>
+</component>

.idea/inspectionProfiles/profiles_settings.xml

@@ -0,0 +1,6 @@
+<component name="InspectionProjectProfileManager">
+  <settings>
+    <option name="USE_PROJECT_PROFILE" value="false" />
+    <version value="1.0" />
+  </settings>
+</component>

.idea/modules.xml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/ai-interviewer-demo.iml" filepath="$PROJECT_DIR$/.idea/ai-interviewer-demo.iml" />
+    </modules>
+  </component>
+</project>

.idea/vcs.xml

@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="VcsDirectoryMappings">
+    <mapping directory="" vcs="Git" />
+  </component>
+</project>

app.py

@@ -1697,7 +1697,7 @@ import os
 import json
 from transformers import BarkModel, AutoProcessor
 import torch, gc
-import whisper
+from faster_whisper import WhisperModel
 import asyncio
 import threading
 from concurrent.futures import ThreadPoolExecutor
@@ -1709,7 +1709,7 @@ gc.collect()
 # Global variables for lazy loading
 model_bark = None
 processor_bark = None
-whisper_model = None
+faster_whisper_model = None
 bark_voice_preset = "v2/en_speaker_6"
 
 # Thread pool for async operations
@@ -1726,7 +1726,7 @@ else:
 
 def load_models_lazy():
     """Load models only when needed"""
-    global model_bark, processor_bark, whisper_model
+    global model_bark, processor_bark, faster_whisper_model
     
     device = "cuda" if torch.cuda.is_available() else "cpu"
     print(f"🔁 Using device: {device}")
@@ -1740,11 +1740,13 @@ def load_models_lazy():
         print("🔁 Loading Bark processor...")
         processor_bark = AutoProcessor.from_pretrained("suno/bark")
         print("✅ Bark processor loaded")
-        
-    if whisper_model is None:
-        print("🔁 Loading Whisper model...")
-        whisper_model = whisper.load_model("base", device=device)
-        print(f"✅ Whisper model loaded on {device}")
+
+    if faster_whisper_model is None:
+        print("🔁 Loading Faster-Whisper model...")
+        compute_type = "float16" if device == "cuda" else "int8"
+        faster_whisper_model = WhisperModel("base", device=device, compute_type=compute_type)
+        print(f"✅ Faster-Whisper model loaded on {device}")
+
 
 def bark_tts_async(text):
     """Fully correct async TTS generation with Bark"""
@@ -1773,18 +1775,17 @@ def bark_tts_async(text):
 
 
 def whisper_stt(audio_path):
-    """Lazy loading whisper STT"""
-    if not audio_path or not os.path.exists(audio_path): 
+    """STT using Faster-Whisper"""
+    if not audio_path or not os.path.exists(audio_path):
         return ""
-    
-    load_models_lazy()  # Load only when needed
-    
-    # Check what device Whisper is actually using
-    device = "cuda" if torch.cuda.is_available() else "cpu"
-    print(f"🔁 Whisper transcribing on {device}")
-    
-    result = whisper_model.transcribe(audio_path)
-    return result["text"]
+
+    load_models_lazy()
+    print("🔁 Transcribing with Faster-Whisper")
+
+    segments, _ = faster_whisper_model.transcribe(audio_path)
+    transcript = " ".join(segment.text for segment in segments)
+    return transcript.strip()
+
 
 seniority_mapping = {
     "Entry-level": 1, "Junior": 2, "Mid-Level": 3, "Senior": 4, "Lead": 5

requirements.txt

@@ -37,4 +37,5 @@ pip==23.3.1
 accelerate==0.29.3
 huggingface_hub==0.20.3
 textract==1.6.3
-bitsandbytes
+bitsandbytes
+faster-whisper==0.10.0