Update app.py

app.py

@@ -1,6 +1,17 @@
+from __future__ import annotations
+
 import gradio as gr
 import whisper
 from transformers import pipeline
+from gradio.themes.base import Base
+from gradio.themes.utils import colors, fonts, sizes
+from typing import Iterable
+import os
+os.environ["TOKENIZERS_PARALLELISM"] = "false"
+import matplotlib
+#matplotlib.use('TkAgg')
+import matplotlib.pyplot as plt
+
 
 model = whisper.load_model("base")
 sentiment_analysis = pipeline("sentiment-analysis", framework="pt", model="SamLowe/roberta-base-go_emotions")
@@ -71,48 +82,145 @@ def inference(audio, sentiment_option):
 
     return lang.upper(), result.text, sentiment_output
 
-title = """<h1 align="center">🎤 Multilingual ASR 💬</h1>"""
-image_path = "thmbnail.jpg"
+title = """<h1 align="center">Audio Sentiment Analysis</h1>"""
+subtitle = """<h6 align="center">Automatic Speech Recognition</h6>"""
+image_path = "/content/drive/MyDrive/Colab Notebooks/Arquitecture_W.jpg"
 description = """
-💻 This demo showcases a general-purpose speech recognition model called Whisper. It is trained on a large dataset of diverse audio and supports multilingual speech recognition, speech translation, and language identification tasks.<br><br>
-<br>
-⚙️ Components of the tool:<br>
-<br>
-&nbsp;&nbsp;&nbsp;&nbsp; - Real-time multilingual speech recognition<br>
-&nbsp;&nbsp;&nbsp;&nbsp; - Language identification<br>
-&nbsp;&nbsp;&nbsp;&nbsp; - Sentiment analysis of the transcriptions<br>
-<br>
-🎯 The sentiment analysis results are provided as a dictionary with different emotions and their corresponding scores.<br>
-<br>
-😃 The sentiment analysis results are displayed with emojis representing the corresponding sentiment.<br>
-<br>
-✅ The higher the score for a specific emotion, the stronger the presence of that emotion in the transcribed text.<br>
-<br>
-❓ Use the microphone for real-time speech recognition.<br>
+<p align="justify">With cross-modal interaction and AI (tools and pre-trained models in NLP), we can analyze large audio data
+in real-time, such as recorded conversations, customer service calls, or voice recordings, in order to identify and categorize
+emotions (from positive and neutral to sad and angry.</p><br>
+
+Components of the tool:<br>
+&nbsp;&nbsp;&nbsp;&nbsp; - Input: Real-time multilingual<br>
+&nbsp;&nbsp;&nbsp;&nbsp; - Video Call speech recognition<br>
+&nbsp;&nbsp;&nbsp;&nbsp; - Pre-trained model: Whisper<br>
+&nbsp;&nbsp;&nbsp;&nbsp; - Model size: Large with 769M Parameters<br>
+&nbsp;&nbsp;&nbsp;&nbsp; - Encoder/Decoder Arquitecture <br>
+&nbsp;&nbsp;&nbsp;&nbsp; - Transcribe, Translate, and Identify Audio<br>
+&nbsp;&nbsp;&nbsp;&nbsp; - Output: Sentiment analysis<br>
 <br>
-⚡️ The model will transcribe the audio and perform sentiment analysis on the transcribed text.<br>
 """
 
 custom_css = """
-#banner-image {
-    display: block;
+banner-image {
     margin-left: auto;
     margin-right: auto;
 }
-#chat-message {
-    font-size: 14px;
-    min-height: 300px;
+chat-message {
+    font-size: 300px;
+    min-height: 600px;
+}
+
+img {
+  border-radius: 8px;
+  max-width: 100%;
+  height: auto;
 }
+
 """
 
-block = gr.Blocks(css=custom_css)
+#-----Themes config:
+
+class Seafoam(Base):
+    def __init__(
+        self,
+        *,
+        primary_hue: colors.Color | str = colors.emerald,
+        secondary_hue: colors.Color | str = colors.blue,
+        neutral_hue: colors.Color | str = colors.blue,
+        spacing_size: sizes.Size | str = sizes.spacing_md,
+        radius_size: sizes.Size | str = sizes.radius_md,
+        text_size: sizes.Size | str = sizes.text_lg,
+        font: fonts.Font
+        | str
+        | Iterable[fonts.Font | str] = (
+            fonts.GoogleFont("Quicksand"),
+            "ui-sans-serif",
+            "sans-serif",
+        ),
+        font_mono: fonts.Font
+        | str
+        | Iterable[fonts.Font | str] = (
+            fonts.GoogleFont("IBM Plex Mono"),
+            "ui-monospace",
+            "monospace",
+        ),
+    ):
+        super().__init__(
+            primary_hue=primary_hue,
+            secondary_hue=secondary_hue,
+            neutral_hue=neutral_hue,
+            spacing_size=spacing_size,
+            radius_size=radius_size,
+            text_size=text_size,
+            font=font,
+            font_mono=font_mono,
+        )
+        super().set(
+            body_background_fill="repeating-linear-gradient(45deg, *primary_200, *primary_200 10px, *primary_50 10px, *primary_50 20px)",
+            body_background_fill_dark="repeating-linear-gradient(45deg, *primary_800, *primary_800 10px, *primary_900 10px, *primary_900 20px)",
+            button_primary_background_fill="linear-gradient(90deg, *primary_300, *secondary_400)",
+            button_primary_background_fill_hover="linear-gradient(90deg, *primary_200, *secondary_300)",
+            button_primary_text_color="white",
+            button_primary_background_fill_dark="linear-gradient(90deg, *primary_600, *secondary_800)",
+            slider_color="*secondary_300",
+            slider_color_dark="*secondary_600",
+            block_title_text_weight="600",
+            block_border_width="3px",
+            block_shadow="*shadow_drop_lg",
+            button_shadow="*shadow_drop_lg",
+            button_large_padding="32px",
+        )
+
+
+seafoam = Seafoam()
+#
+
+lock_symbol = '\U0001F512' # 🔒
+unlock_symbol = '\U0001F513' # 🔓
+switch_values_symbol = '\U000021C5' # ⇅
+
+class FormRow(gr.Row, gr.components.FormComponent):
+    """Same as gr.Row but fits inside gradio forms"""
+
+    def get_block_name(self):
+        return "row"
+
+class ToolButton(gr.Button, gr.components.FormComponent):
+    """Small button with single emoji as text, fits inside gradio forms"""
+
+    def __init__(self, **kwargs):
+        super().__init__(variant="tool", **kwargs)
+
+    def get_block_name(self):
+        return "button"
+
+def toggle_aspect_ratio(btn):
+    if btn == unlock_symbol:
+        return gr.update(value = lock_symbol, variant="primary")
+    else:
+        return gr.update(value = unlock_symbol, variant="secondary")
+
+
+#
+
+
+
+block = gr.Blocks(css=custom_css, theme='gradio/default',title="Analytics Projects by Ray Espinoza")
+#block = gr.Blocks(css=custom_css, title="Analytics Projects by Ray Espinoza")
+#block = gr.Blocks(css=".gradio-container {background-color: black}", title="Analytics Projects by Ray Espinoza")
+#block = gr.Blocks(css=".gradio-container {background: url('file=pic4.jpg')}", title="Analytics Projects by Ray Espinoza")
 
 with block:
     gr.HTML(title)
+    gr.HTML(subtitle)
 
     with gr.Row():
-        with gr.Column():
-            gr.Image(image_path, elem_id="banner-image", show_label=False)
+        with gr.Column(scale=2):
+            gr.Image(image_path, elem_id="banner-image", show_label=False, show_download_button=False)
+            #banner-image
+            #gr.Markdown(value=image_path, elem_id="img")
+            #gr.Image(image_path, elem_id="chat-message", show_label=False)
         with gr.Column():
             gr.HTML(description)
 
@@ -120,7 +228,7 @@ with block:
         with gr.Box():
             audio = gr.Audio(
                 label="Input Audio",
-                show_label=False,
+                show_label=False,#Here#False
                 source="microphone",
                 type="filepath"
             )
@@ -131,21 +239,21 @@ with block:
                 default="Sentiment Only"
             )
 
-            btn = gr.Button("Transcribe")
+            btn = gr.Button("Execute: Transcribe",variant="primary")
 
-        lang_str = gr.Textbox(label="Language")
+        lang_str = gr.Textbox(label="Language:")
 
-        text = gr.Textbox(label="Transcription")
+        text = gr.Textbox(label="Transcription:")
 
-        sentiment_output = gr.Textbox(label="Sentiment Analysis Results", output=True)
+        sentiment_output = gr.Textbox(label="Sentiment Analysis Results:", output=True)
 
         btn.click(inference, inputs=[audio, sentiment_option], outputs=[lang_str, text, sentiment_output])
 
         gr.HTML('''
         <div class="footer">
-            <p>Model by <a href="https://github.com/openai/whisper" style="text-decoration: underline;" target="_blank">Ray Espinoza</a>
+            <p>By <a href="https://github.com/rayespinozah" style="text-decoration: underline;" target="_blank"> Ray Espinoza Github</a>
             </p>
         </div>
-        ''') 
+        ''')
 
-block.launch()
+block.launch(share=True)