Add application file

requirements.txt

@@ -0,0 +1,148 @@
+absl-py==2.1.0
+aiofiles==23.2.1
+aiohappyeyeballs==2.4.3
+aiohttp==3.10.10
+aiosignal==1.3.1
+annotated-types==0.7.0
+anyascii==0.3.2
+anyio==4.6.2.post1
+attrs==24.2.0
+audioread==3.0.1
+babel==2.16.0
+blis==0.7.11
+catalogue==2.0.10
+certifi==2024.8.30
+cffi==1.17.1
+charset-normalizer==3.4.0
+click==8.1.7
+cloudpathlib==0.19.0
+confection==0.1.5
+contourpy==1.3.0
+coqpit==0.0.17
+coqui-tts==0.24.2
+coqui-tts-trainer==0.1.4
+cutlet==0.4.0
+cycler==0.12.1
+cymem==2.0.8
+Cython==3.0.11
+dateparser==1.1.8
+decorator==5.1.1
+docopt==0.6.2
+einops==0.8.0
+encodec==0.1.1
+fastapi==0.115.2
+ffmpy==0.4.0
+filelock==3.16.1
+fonttools==4.54.1
+frozenlist==1.4.1
+fsspec==2024.9.0
+fugashi==1.3.2
+gradio==5.1.0
+gradio_client==1.4.0
+grpcio==1.66.2
+gruut==2.4.0
+gruut-ipa==0.13.0
+gruut_lang_de==2.0.1
+gruut_lang_en==2.0.1
+gruut_lang_es==2.0.1
+gruut_lang_fr==2.0.2
+h11==0.14.0
+httpcore==1.0.6
+httpx==0.27.2
+huggingface-hub==0.25.2
+idna==3.10
+inflect==7.4.0
+jaconv==0.4.0
+Jinja2==3.1.4
+joblib==1.4.2
+jsonlines==1.2.0
+kiwisolver==1.4.7
+langcodes==3.4.1
+language_data==1.2.0
+lazy_loader==0.4
+librosa==0.10.2.post1
+llvmlite==0.43.0
+marisa-trie==1.2.1
+Markdown==3.7
+markdown-it-py==3.0.0
+MarkupSafe==2.1.5
+matplotlib==3.9.2
+mdurl==0.1.2
+mojimoji==0.0.13
+more-itertools==10.5.0
+mpmath==1.3.0
+msgpack==1.1.0
+multidict==6.1.0
+murmurhash==1.0.10
+networkx==3.4.1
+num2words==0.5.13
+numba==0.60.0
+numpy==1.26.4
+orjson==3.10.7
+packaging==24.1
+pandas==2.2.3
+pillow==10.4.0
+platformdirs==4.3.6
+pooch==1.8.2
+preshed==3.0.9
+propcache==0.2.0
+protobuf==5.28.2
+psutil==6.0.0
+pycparser==2.22
+pydantic==2.9.2
+pydantic_core==2.23.4
+pydub==0.25.1
+Pygments==2.18.0
+pyparsing==3.2.0
+pysbd==0.3.4
+python-crfsuite==0.9.11
+python-dateutil==2.9.0.post0
+python-multipart==0.0.12
+pytz==2024.2
+PyYAML==6.0.2
+regex==2024.9.11
+requests==2.32.3
+rich==13.9.2
+ruff==0.7.0
+safetensors==0.4.5
+scikit-learn==1.5.2
+scipy==1.14.1
+semantic-version==2.10.0
+setuptools==75.1.0
+shellingham==1.5.4
+six==1.16.0
+smart-open==7.0.5
+sniffio==1.3.1
+soundfile==0.12.1
+soxr==0.5.0.post1
+spacy==3.7.5
+spacy-legacy==3.0.12
+spacy-loggers==1.0.5
+srsly==2.4.8
+starlette==0.40.0
+SudachiDict-core==20240716
+SudachiPy==0.6.8
+sympy==1.13.3
+tensorboard==2.18.0
+tensorboard-data-server==0.7.2
+thinc==8.2.5
+threadpoolctl==3.5.0
+tokenizers==0.19.1
+tomlkit==0.12.0
+torch==2.4.1
+torchaudio==2.4.1
+tqdm==4.66.5
+transformers==4.42.4
+typeguard==4.3.0
+typer==0.12.5
+typing_extensions==4.12.2
+tzdata==2024.2
+tzlocal==5.2
+urllib3==2.2.3
+uvicorn==0.32.0
+wasabi==1.1.3
+weasel==0.4.1
+websockets==12.0
+Werkzeug==3.0.4
+wrapt==1.16.0
+yarl==1.15.2

tts-app.py

@@ -0,0 +1,179 @@
+# TODO#1 - Importing Required Libraries
+import gradio as gr
+from TTS.api import TTS
+import numpy as np
+import time
+import os
+import matplotlib.pyplot as plt
+from scipy.io import wavfile
+
+# TODO#2 - Loading the Coqui TTS Model
+model_name = TTS.list_models()[0]
+tts = TTS(model_name)
+
+# TODO#3 - Defining Voice Selection
+avilable_speakers = [
+    "Daisy Studious", "Sofia Hellen", "Asya Anara",
+    "Eugenio Mataracı", "Viktor Menelaos", "Damien Black" 
+]
+
+
+# TODO#4 - Defining Localization Options
+avilable_languages = [
+    "US English", "Spanish (LatAm)"
+]
+
+# TODO#5 - Defining Variables to Hold Selected Voice and Localization
+selected_speaker = avilable_speakers[0]
+selected_languages= avilable_languages[0]
+
+
+# TODO#6 - Managing Outputs
+os.makedirs("output", exist_ok=True)
+last_generated_audio = None
+last_generated_text = ""
+
+# TODO#7 - Implementing the Trim Function.
+def trim_text(text, max_length=30):
+    return text[:max_length] + '...' if len(text) > max_length else text
+
+
+# Main Speech Synthesis Function
+def generate_speech_with_timestamps(text, speaker, language):
+    global last_generated_audio, last_generated_text
+    output_path = "output/generated_speech.wav"
+    start_time = time.time()
+
+    # TODO#8 - Implementing the Main TTS Function
+    tts.tts_to_file(
+        text=text,
+        speaker=speaker,
+        language= 'en' if language == "US English" else 'es',
+        file_path = output_path
+    )
+
+
+    # TODO#9 - Managing Duration and Tracking Variables
+    end_time = time.time()
+    duration = round(end_time - start_time, 2)
+    last_generated_audio = output_path
+    last_generated_text = text
+
+
+    # TODO#10 - Extracting Audio Information
+    samplerate, data = wavfile.read(output_path)
+    speech_length = len(data) / samplerate
+
+
+    # TODO#11 - Return Audio Information
+    return output_path, len(text.split()), speaker, language, round(speech_length, 2), duration
+
+
+# Waveform Function
+def generate_waveform():
+    # Initialize Global Variables and Input Validation
+    global last_generated_audio, last_generated_text
+
+    # Check if a valid audio file exists
+    if not last_generated_audio or not os.path.exists(last_generated_audio):
+        return None, 'No valid audiofile to generate waveform'
+
+       # Read Audio File and Create Time Axis
+    samplerate, data = wavfile.read(last_generated_audio)
+    time_axis = np.linspace(0, len(data)/ samplerate, num=len(data))
+
+    # Plot the Waveform with Custom Styling
+    fig, ax = plt.subplots(figsize=(8,4), facecolor='#1E1E1E') # Dark background
+
+    # Plot the Waveform with Custom Styling
+    ax.plot(time_axis, data, alpha=0.8, color=cyan, linewidth=1.2)
+
+    # Styling grid and axes for a modern look
+    ax.set_facecolor('#2E2E2E') # Set darker plot background
+    ax.grid(color='gray', linestyle='--', linewidth=0.5, alpha=0.5 ) # Add grid lines
+    ax.spines['bottom'].set_color('white')  # Set bottom spine color to white
+    ax.spines['left'].set_color('white')  # Set left spine color to white
+    ax.tick_params(axix='x', colors='white')  # Set x-axis tick color
+    ax.tick_params(axix='y', colors='white')  # Set y-axis tick color
+    ax.set_xlabel('Time (seconds)', color='white')  # Label x-axis
+    ax.set_ylabel('Amplitude', color='white') # Label y-axis
+
+    # Add a Title to the Plot
+    # Trim long text for display in title
+    trimed_text = trim_text(last_generated_text)
+    ax.set_title(f'Waveform for text input: {trimed_}')
+
+    # Save the waveform image
+    waveform_image_path = "output/waveform.png"
+    plt.savefig(waveform_image_path, transparent=True)
+    plt.close()
+
+    return waveform_image_path, "Waveform generated successfully!"
+
+# Button Click Event Handler
+def generate_speech(text, speaker, language):
+    if not text:
+        return None, "Please enter some text to generate speech", "", gr.update(interactive = False)
+
+    audio_path, word_count, speaker_name, lang, speech_length, duration = generate_speech_with_timestamps(text, speaker, language)
+
+    # Format the text box content
+    data_info = f"Word Count: {word_count}\nVoice: {speaker_name}\nLocalization: {lang}\nLength of Speech: {speech_length} seconds\nGeneration Duration: {duration} seconds"
+
+    return audio_path, data_info, "Speech generation successful!", gr.update(interactive=True)
+
+# Gradio Interface Setup
+def setup_interface():
+    with gr.Blocks() as app:
+        # TODO#12 - Adding Title and Description
+        gr.Markdown('# 🗣️ Text-to-Speech GenAI with Coqui TTS')
+        gr.Markdown('Convert text to speech using Coqui TTS with support for different languages and speakers.')
+
+
+        with gr.Row():
+            with gr.Column():
+
+                # TODO#13 - Creating Text Input
+                text_input = gr.Textbox(label='', placeholder='Type your text here', lines=3)
+
+                with gr.Row():
+                    # TODO#14 - Creating Voice and Localization Options
+                    speaker_dropdown = gr.Dropdown(choices=avilable_speakers, value=selected_speaker, label='Select Voice')
+                    language_radio = gr.Radio(choices=avilable_languages, value=selected_languages, label = 'Select Localization')
+
+            with gr.Column():
+                # TODO#15 - Displaying Data Information and Status
+                data_info_display = gr.Textbox(label = 'Data Info', interactive=False, lines=5)
+                status_message = gr.Textbox(label = 'Status', interactive = False)
+
+
+        with gr.Row():
+            with gr.Column():
+                # TODO#16 - Adding Audio Output and "Generate Speech" Button
+                audio_output = gr.Audio(label = 'Generated Speech', interactive = False)
+                generate_button = gr.Button('Generate Speech')
+
+
+            with gr.Column():
+                # TODO#17 - Adding Waveform Display and "Generate Waveform" Button
+                waveform_output = gr.Image(label = 'waveform')
+                generate_waveform_button = gr.Button('Generate Waveform', interactive = False)
+
+
+        generate_button.click(
+            generate_speech, 
+            inputs=[text_input, speaker_dropdown, language_radio], 
+            outputs=[audio_output, data_info_display, status_message, generate_waveform_button]
+        )
+
+        generate_waveform_button.click(
+            generate_waveform, 
+            outputs=[waveform_output, status_message]
+        )
+
+    return app
+
+# TODO#18 - Launching the App
+if __name__ == '__main__':
+    app = setup_interface()
+    app.launch(share=True)