Update app.py

app.py

@@ -3,7 +3,6 @@ import openai
 from kokoro import KPipeline
 import soundfile as sf
 import io
-import time
 
 # Streamlit App UI Setup
 st.title("Text-to-Speech Translator with Kokoro")
@@ -59,6 +58,71 @@ st.sidebar.markdown("""
 - Enjoy exploring different languages, voices, and speeds with the text-to-speech conversion!
 """)
 
+# Custom HTML and CSS for Spinner
+st.markdown("""
+<style>
+.lds-ellipsis,
+.lds-ellipsis div {
+  box-sizing: border-box;
+}
+.lds-ellipsis {
+  display: inline-block;
+  position: relative;
+  width: 80px;
+  height: 80px;
+}
+.lds-ellipsis div {
+  position: absolute;
+  top: 33.33333px;
+  width: 13.33333px;
+  height: 13.33333px;
+  border-radius: 50%;
+  background: currentColor;
+  animation-timing-function: cubic-bezier(0, 1, 1, 0);
+}
+.lds-ellipsis div:nth-child(1) {
+  left: 8px;
+  animation: lds-ellipsis1 0.6s infinite;
+}
+.lds-ellipsis div:nth-child(2) {
+  left: 8px;
+  animation: lds-ellipsis2 0.6s infinite;
+}
+.lds-ellipsis div:nth-child(3) {
+  left: 32px;
+  animation: lds-ellipsis2 0.6s infinite;
+}
+.lds-ellipsis div:nth-child(4) {
+  left: 56px;
+  animation: lds-ellipsis3 0.6s infinite;
+}
+@keyframes lds-ellipsis1 {
+  0% {
+    transform: scale(0);
+  }
+  100% {
+    transform: scale(1);
+  }
+}
+@keyframes lds-ellipsis3 {
+  0% {
+    transform: scale(1);
+  }
+  100% {
+    transform: scale(0);
+  }
+}
+@keyframes lds-ellipsis2 {
+  0% {
+    transform: translate(0, 0);
+  }
+  100% {
+    transform: translate(24px, 0);
+  }
+}
+</style>
+""", unsafe_allow_html=True)
+
 # User input for text, language, and voice settings
 input_text = st.text_area("Enter your text here", placeholder="The sky above the port was the color of television...")
 lang_code = st.selectbox("Select Language", ['a', 'b', 'e', 'f', 'h', 'i', 'p', 'z', 'j'])
@@ -116,57 +180,51 @@ def translate_to_english(api_key, text, lang_code):
 # Generate Audio function
 def generate_audio(text, lang_code, voice, speed):
     generator = pipeline(text, voice=voice, speed=speed, split_pattern=r'\n+')
-    audio_data = None
     for i, (gs, ps, audio) in enumerate(generator):
         audio_data = audio
-        time.sleep(1)  # Simulate processing delay for the spinner (this can be removed or adjusted)
-    # Save audio to in-memory buffer
-    buffer = io.BytesIO()
-    # Explicitly specify format as WAV
-    sf.write(buffer, audio_data, 24000, format='WAV')  # Add 'format="WAV"'
-    buffer.seek(0)
-    return buffer
+        # Save audio to in-memory buffer
+        buffer = io.BytesIO()
+        # Explicitly specify format as WAV
+        sf.write(buffer, audio_data, 24000, format='WAV')  # Add 'format="WAV"'
+        buffer.seek(0)
+        return buffer
 
 # Generate and display the audio file
 if st.button('Generate Audio'):
 
-    # Show the spinner with percentage count
-    with st.spinner("Generating audio... 0%"):
-        for i in range(1, 101, 10):
-            time.sleep(0.5)  # Simulate work being done, you can adjust timing here
-            st.spinner(f"Generating audio... {i}%")
-        
-        # Generate audio for the original text after the spinner
+    # Display spinner during audio generation
+    with st.spinner('Generating audio...'):
+        # Generate audio for the original text
         st.write("Generating speech for the original text...")
         audio_buffer = generate_audio(input_text, lang_code, voice, speed)
-    
-    # Display Audio player for the original language
-    st.audio(audio_buffer, format='audio/wav')
-
-    # Optional: Save the generated audio file for download (Original Text)
-    st.download_button(
-        label="Download Audio (Original Text)",
-        data=audio_buffer,
-        file_name="generated_speech_original.wav",
-        mime="audio/wav"
-    )
-
-    # Check if OpenAI API Key is provided for translation and English audio generation
-    if openai_api_key:
-        # Translate the input text to English using OpenAI
-        translated_text = translate_to_english(openai_api_key, input_text, lang_code)
-
-        # Generate audio for the translated English text
-        translated_audio_buffer = generate_audio(translated_text, 'a', voice, speed)
-
-        # Display Audio for the translated text
-        st.write(f"Translated Text: {translated_text}")
-        st.audio(translated_audio_buffer, format='audio/wav')
-
-        # Optional: Save the generated audio file for download (Translated Text)
+        
+        # Display Audio player for the original language
+        st.audio(audio_buffer, format='audio/wav')
+
+        # Optional: Save the generated audio file for download (Original Text)
         st.download_button(
-            label="Download Audio (Translated to English)",
-            data=translated_audio_buffer,
-            file_name="generated_speech_translated.wav",
+            label="Download Audio (Original Text)",
+            data=audio_buffer,
+            file_name="generated_speech_original.wav",
             mime="audio/wav"
         )
+
+        # Check if OpenAI API Key is provided for translation and English audio generation
+        if openai_api_key:
+            # Translate the input text to English using OpenAI
+            translated_text = translate_to_english(openai_api_key, input_text, lang_code)
+
+            # Generate audio for the translated English text
+            translated_audio_buffer = generate_audio(translated_text, 'a', voice, speed)
+
+            # Display Audio for the translated text
+            st.write(f"Translated Text: {translated_text}")
+            st.audio(translated_audio_buffer, format='audio/wav')
+
+            # Optional: Save the generated audio file for download (Translated Text)
+            st.download_button(
+                label="Download Audio (Translated to English)",
+                data=translated_audio_buffer,
+                file_name="generated_speech_translated.wav",
+                mime="audio/wav"
+            )