Update app.py

app.py

@@ -24,6 +24,7 @@ DATASET_REPO_ID = "awacke1/MindfulStory.csv"
 DATA_FILENAME = "MindfulStory.csv"
 DATA_FILE = os.path.join("data", DATA_FILENAME)
 HF_TOKEN = os.environ.get("HF_TOKEN")
+
 # Download dataset repo using hub download
 try:
     hf_hub_download(
@@ -47,12 +48,12 @@ with open('Mindfulness.txt', 'r') as file:
         context = file.read()
    
 # Set up cloned dataset from repo for operations
-repo = Repository(
-    local_dir="data", clone_from=DATASET_REPO_URL, use_auth_token=HF_TOKEN
-)
+repo = Repository( local_dir="data", clone_from=DATASET_REPO_URL, use_auth_token=HF_TOKEN)
 
+# set up ASR
 asr = pipeline("automatic-speech-recognition", "facebook/wav2vec2-base-960h")
 
+# set up TTS
 MODEL_NAMES = [
     "en/ljspeech/tacotron2-DDC",
     "en/ljspeech/glow-tts",
@@ -62,6 +63,8 @@ MODEL_NAMES = [
     "fr/mai/tacotron2-DDC",
     "de/thorsten/tacotron2-DCA",
 ]
+
+# Use Model Manager to load vocoders
 MODELS = {}
 manager = ModelManager()
 for MODEL_NAME in MODEL_NAMES:
@@ -78,24 +81,23 @@ for MODEL_NAME in MODEL_NAMES:
     )
     MODELS[MODEL_NAME] = synthesizer
 
+# transcribe
 def transcribe(audio):
     text = asr(audio)["text"]
     return text
 
+#text classifier
 classifier = pipeline("text-classification")
 
+
 def speech_to_text(speech):
     text = asr(speech)["text"]
-    
     #rMem = AIMemory("STT", text) 
-    
     return text
 
 def text_to_sentiment(text):
     sentiment = classifier(text)[0]["label"]
-    
     #rMem = AIMemory(text, sentiment) 
-
     return sentiment 
 
 def upsert(text):
@@ -103,8 +105,6 @@ def upsert(text):
     doc_ref = db.collection('Text2SpeechSentimentSave').document(date_time)
     doc_ref.set({u'firefield': 'Recognize Speech', u'first': 'https://huggingface.co/spaces/awacke1/TTS-STT-Blocks/', u'last': text, u'born': date_time,})
     saved = select('TTS-STT', date_time)
- 
-    
     return saved
       
 def select(collection, document):
@@ -138,11 +138,11 @@ def tts(text: str, model_name: str):
 demo = gr.Blocks()
 with demo:
     audio_file = gr.inputs.Audio(source="microphone", type="filepath")
-    text = gr.Textbox()
+    text = gr.Textbox(label="Speech to Text")
     label = gr.Label()
-    saved = gr.Textbox()
-    savedAll = gr.Textbox()
-    TTSchoice = gr.inputs.Radio( label="Pick a TTS Model", choices=MODEL_NAMES,   )
+    saved = gr.Textbox(label="Saved")
+    savedAll = gr.Textbox(label="SavedAll")
+    TTSchoice = gr.inputs.Radio( label="Pick a Text to Speech Model", choices=MODEL_NAMES,   )
     audio = gr.Audio(label="Output", interactive=False)
     
     b1 = gr.Button("Recognize Speech")