Update app.py

app.py

@@ -2,40 +2,37 @@ import streamlit as st
 import datetime
 from transformers import pipeline
 import gradio as gr
-
 import tempfile
 from typing import Optional
 import numpy as np
 from TTS.utils.manage import ModelManager
 from TTS.utils.synthesizer import Synthesizer
-
-# PersistDataset -----
 import os
 import csv
-import gradio as gr
-from gradio import inputs, outputs
 import huggingface_hub
 from huggingface_hub import Repository, hf_hub_download, upload_file
 from datetime import datetime
 
-# created new dataset as awacke1/MindfulStory.csv
+# 🌟 Setup dataset repo 🌟
+# Created new dataset as awacke1/MindfulStory.csv
 DATASET_REPO_URL = "https://huggingface.co/datasets/awacke1/MindfulStory.csv"
 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
+# 😅 Oops! Try downloading the dataset (We hope it works!)
 try:
     hf_hub_download(
         repo_id=DATASET_REPO_ID,
         filename=DATA_FILENAME,
-        cache_dir=DATA_DIRNAME,
+        cache_dir="data",
         force_filename=DATA_FILENAME
     )
 except:
-    print("file not found")
-    
+    print("😬 File not found, we’ll act like it’s not a problem...")
+
+# 🧠 AI Memory: Because forgetting is for humans 🤖
 def AIMemory(name: str, message: str):
     if name and message:
         with open(DATA_FILE, "a") as csvfile:
@@ -44,16 +41,13 @@ def AIMemory(name: str, message: str):
         commit_url = repo.push_to_hub()
     return {"name": name, "message": message, "time": str(datetime.now())}
 
-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)
+# 🌍 Repository setup! Let’s clone like pros 👨‍💻
+repo = Repository(local_dir="data", clone_from=DATASET_REPO_URL, use_auth_token=HF_TOKEN)
 
-# set up ASR
+# 🗣️ Set up Speech Recognition
 asr = pipeline("automatic-speech-recognition", "facebook/wav2vec2-base-960h")
 
-# set up TTS
+# 🎤 Set up TTS Models. Let’s find that sweet robotic voice!
 MODEL_NAMES = [
     "en/ljspeech/tacotron2-DDC",
     "en/ljspeech/glow-tts",
@@ -64,11 +58,11 @@ MODEL_NAMES = [
     "de/thorsten/tacotron2-DCA",
 ]
 
-# Use Model Manager to load vocoders
+# 🛠️ Use Model Manager to load vocoders (Fancy tech magic here)
 MODELS = {}
 manager = ModelManager()
 for MODEL_NAME in MODEL_NAMES:
-    print(f"downloading {MODEL_NAME}")
+    print(f"🚀 Downloading {MODEL_NAME}... because waiting is fun!")
     model_path, config_path, model_item = manager.download_model(f"tts_models/{MODEL_NAME}")
     vocoder_name: Optional[str] = model_item["default_vocoder"]
     vocoder_path = None
@@ -81,80 +75,80 @@ for MODEL_NAME in MODEL_NAMES:
     )
     MODELS[MODEL_NAME] = synthesizer
 
-# transcribe
+# 🧙‍♂️ Transcribe function: Turning audio into text with a sprinkle of magic!
 def transcribe(audio):
     text = asr(audio)["text"]
     return text
 
-#text classifier
+# 📊 Text classifier (because we love labeling things, right?)
 classifier = pipeline("text-classification")
 
-
+# 🎤 Speech to Text: Give me your voice, I’ll give you text!
 def speech_to_text(speech):
     text = asr(speech)["text"]
-    #rMem = AIMemory("STT", text) 
     return text
 
+# 😎 Sentiment Analysis (because even robots care about feelings 💔)
 def text_to_sentiment(text):
     sentiment = classifier(text)[0]["label"]
-    #rMem = AIMemory(text, sentiment) 
     return sentiment 
 
+# 📦 Saving it for later: Store this priceless info!
 def upsert(text):
-    date_time =str(datetime.datetime.today())
+    date_time = str(datetime.datetime.today())
     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,})
+    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):
-    doc_ref = db.collection(collection).document(document)
-    doc = doc_ref.get()
-    docid = ("The id is: ", doc.id)
-    contents = ("The contents are: ", doc.to_dict())
-    return contents
-          
+
+# 🔍 Retrieve all records: Gotta catch ‘em all!
 def selectall(text):
     docs = db.collection('Text2SpeechSentimentSave').stream()
-    doclist=''
+    doclist = ''
     for doc in docs:
-        r=(f'{doc.id} => {doc.to_dict()}')
+        r = (f'{doc.id} => {doc.to_dict()}')
         doclist += r
     return doclist 
-    
+
+# 🗣️ Text to Speech (Because speaking is fun, but robots do it better)
 def tts(text: str, model_name: str):
     print(text, model_name)
     synthesizer = MODELS.get(model_name, None)
     if synthesizer is None:
-        raise NameError("model not found")
+        raise NameError("😬 Oops! Model not found.")
+    
     wavs = synthesizer.tts(text)
     with tempfile.NamedTemporaryFile(suffix=".wav", delete=False) as fp:
         synthesizer.save_wav(wavs, fp)
-        
-        #rMem = AIMemory("TTS", text + model_name) 
-    
         return fp.name
 
+# 🎛️ Gradio UI with Emoji and Fun Comments 🎉
 demo = gr.Blocks()
+
 with demo:
-    audio_file = gr.inputs.Audio(source="microphone", type="filepath")
+    # 🎤 Microphone input to capture your golden voice 🎤
+    audio_file = gr.Audio(source="microphone", type="filepath")
+    
+    # 📜 Textbox to display transcribed text 📜
     text = gr.Textbox(label="Speech to Text")
-    #label = gr.Label()
-    #saved = gr.Textbox(label="Saved")
-    #savedAll = gr.Textbox(label="SavedAll")
-    TTSchoice = gr.inputs.Radio( label="Pick a Text to Speech Model", choices=MODEL_NAMES,   )
+    
+    # 🎙️ Radio input to choose the best Text to Speech model 🎙️
+    TTSchoice = gr.Radio(label="Pick a Text to Speech Model", choices=MODEL_NAMES)
+    
+    # 🔊 Audio player to play back the robot’s voice 🔊
     audio = gr.Audio(label="Output", interactive=False)
     
-    b1 = gr.Button("Recognize Speech")
-    #b2 = gr.Button("Classify Sentiment")
-    #b3 = gr.Button("Save Speech to Text")
-    #b4 = gr.Button("Retrieve All")
-    b5 = gr.Button("Read It Back Aloud")
-
+    # 🎉 Buttons for all your needs 🎉
+    b1 = gr.Button("🎤 Recognize Speech")
+    b5 = gr.Button("🔊 Read It Back Aloud")
+    
+    # 🖱️ Click buttons to perform actions! 🖱️
     b1.click(speech_to_text, inputs=audio_file, outputs=text)
-    #b2.click(text_to_sentiment, inputs=text, outputs=label)
-    #b3.click(upsert, inputs=text, outputs=saved)
-    #b4.click(selectall, inputs=text, outputs=savedAll)
-    b5.click(tts,  inputs=[text,TTSchoice], outputs=audio)
+    b5.click(tts, inputs=[text, TTSchoice], outputs=audio)
     
-demo.launch(share=True)
+demo.launch(share=True)