First commit

README.md

@@ -3,8 +3,8 @@ title: Text To Voice
 emoji: 👁
 colorFrom: green
 colorTo: yellow
-sdk: gradio
-sdk_version: 4.36.1
+sdk: streamlit
+sdk_version: 1.28.2
 app_file: app.py
 pinned: false
 ---

app.py

@@ -0,0 +1,91 @@
+import streamlit as st
+import numpy as np
+import torch
+from transformers import SpeechT5Processor, SpeechT5ForTextToSpeech, SpeechT5HifiGan
+import soundfile as sf
+from io import StringIO
+
+# Load models outside of function calls for efficiency
+@st.cache(allow_output_mutation=True)
+def load_models():
+    model = SpeechT5ForTextToSpeech.from_pretrained("microsoft/speecht5_tts")
+    processor = SpeechT5Processor.from_pretrained("microsoft/speecht5_tts")
+    vocoder = SpeechT5HifiGan.from_pretrained("microsoft/speecht5_hifigan")
+    return model, processor, vocoder
+
+model, processor, vocoder = load_models()
+
+# Load speaker embeddings
+@st.cache(allow_output_mutation=True)
+def get_speaker_embeddings():
+    speaker_embeddings = np.load("cmu_us_clb_arctic-wav-arctic_a0144.npy")
+    return torch.tensor(speaker_embeddings).unsqueeze(0)
+
+speaker_embeddings = get_speaker_embeddings()
+
+# Improved Styling (assuming style.css is present)
+def local_css(file_name):
+    with open(file_name) as f:
+        st.markdown(f'<style>{f.read()}</style>', unsafe_allow_html=True)
+
+local_css("style.css")  # Apply custom CSS styles
+
+# Streamlit Layout
+st.title("Text-to-Voice Conversion")
+st.markdown("Convert your text to speech using advanced AI models.")
+
+# Function to convert text to speech
+def text_to_speech(text):
+    try:
+        max_length = 100  # Set a max length as per model's capability
+        segments = [text[i:i+max_length] for i in range(0, len(text), max_length)]
+        audio_paths = []
+
+        for i, segment in enumerate(segments):
+            inputs = processor(text=segment, return_tensors="pt")
+            spectrogram = model.generate_speech(inputs["input_ids"], speaker_embeddings)
+            with torch.no_grad():
+                speech = vocoder(spectrogram)
+                audio_path = f"speech_segment_{i}.wav"
+                sf.write(audio_path, speech.numpy(), samplerate=16000)
+                audio_paths.append(audio_path)
+
+        return audio_paths
+    except Exception as e:
+        st.error(f"Error in text-to-speech conversion: {e}")
+        return []
+
+# Function to combine audio segments
+def combine_audio_segments(paths):
+    combined_speech = []
+    for path in paths:
+        data, samplerate = sf.read(path)
+        combined_speech.extend(data)
+    sf.write("combined_speech.wav", np.array(combined_speech), samplerate)
+    return "combined_speech.wav"
+
+# Text Input and Conversion Button
+text = st.text_area("Type your text here.")
+
+if st.button("Convert"):
+    if text:
+        audio_paths = text_to_speech(text)
+        combined_audio_path = combine_audio_segments(audio_paths)
+        audio_bytes = open(combined_audio_path, 'rb').read()
+        st.audio(audio_bytes, format='audio/wav')
+    else:
+        st.error("Please enter some text to convert.")
+
+# File Uploader and Conversion Button
+uploaded_file = st.file_uploader("Upload a text file here", type=['txt'])
+
+if uploaded_file is not None:
+    stringio = StringIO(uploaded_file.getvalue().decode("utf-8"))
+    text = stringio.read()
+    st.write(text)
+
+    if st.button("Convert Uploaded File", key="upload"):
+        audio_paths = text_to_speech(text)
+        combined_audio_path = combine_audio_segments(audio_paths)
+        audio_bytes = open(combined_audio_path, 'rb').read()
+        st.audio(audio_bytes, format='audio/wav')

cmu_us_awb_arctic-wav-arctic_a0002.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5db7a684ab490f21cec1628e00d461a184e369fe4eafb1ee441a796faf4ab6ae
+size 2176

cmu_us_bdl_arctic-wav-arctic_a0009.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:215326eae3a428af8934c385fbe043b36c72849ca17d1d013adeb189e6bd6962
+size 2176

cmu_us_clb_arctic-wav-arctic_a0144.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf67b36c47edfb1851466a1dff081b436bc6809b5ebc12811d9df0c0d0f28d0e
+size 2176

cmu_us_ksp_arctic-wav-arctic_b0087.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6c5c2a38c2e400179019c560a74c4322f4ee13beda22ee601807545edee283e
+size 2176

cmu_us_rms_arctic-wav-arctic_b0353.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a49dac3e9c3a71a4dbca4c364233c7915ae6e0cb71b2ceaed97296231b95cb50
+size 2176

cmu_us_slt_arctic-wav-arctic_a0508.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f71ffadda3f3a4de079740a0b34963824dc644d9d5442283bd0a2b0d4f44ff0b
+size 2176

requirements.txt

@@ -0,0 +1,11 @@
+streamlit_option_menu == 0.3.2
+requests==2.28.1
+streamlit-lottie==0.0.3
+times==0.7
+htbuilder==0.6.1
+transformers==4.29.2
+torch==2.0.1
+soundfile==0.12.1
+torchaudio == 2.0.2
+sentencepiece==0.1.99
+streamlit

style.css

@@ -0,0 +1,49 @@
+/* Custom CSS for Streamlit App */
+
+/* Header Style */
+header {
+    background-color: #5072A7; /* A soothing shade of blue */
+    color: white; /* White text for contrast */
+    padding: 10px; /* Adding padding for spacing */
+}
+
+/* Main Body Style */
+body {
+    font-family: Arial, sans-serif; /* Standard readable font stack */
+    color: #333333; /* Dark grey color for main text */
+    line-height: 1.6; /* Improved line spacing for readability */
+}
+
+/* Titles and Headings */
+h1, h2, h3 {
+    color: #333366; /* Darker shade of blue for headings */
+    margin-bottom: 10px; /* Adding margin for separation */
+}
+
+/* Buttons */
+button {
+    background-color: #4CAF50; /* Green background for buttons */
+    color: white; /* White text for contrast */
+    padding: 10px 20px; /* Padding for button size */
+    margin: 10px 0; /* Margin for spacing */
+    border: none; /* Removing default border */
+    cursor: pointer; /* Pointer cursor for usability */
+    border-radius: 5px; /* Rounded corners */
+    transition: background-color 0.3s ease; /* Smooth hover transition */
+}
+
+button:hover {
+    background-color: #45a049; /* Darker green on hover */
+}
+
+/* Footer Style */
+footer {
+    background-color: #333333; /* Dark background for footer */
+    color: white; /* White text for contrast */
+    text-align: center; /* Center-aligning text */
+    padding: 10px; /* Padding for spacing */
+    position: fixed; /* Fixed positioning */
+    left: 0;
+    bottom: 0;
+    width: 100%; /* Full width */
+}