Update src/streamlit_app.py

src/streamlit_app.py

@@ -1,40 +1,76 @@
-import altair as alt
-import numpy as np
-import pandas as pd
 import streamlit as st
+from kokoro import KPipeline
+import soundfile as sf
+import tempfile
 
-"""
-# Welcome to Streamlit!
-
-Edit `/streamlit_app.py` to customize this app to your heart's desire :heart:.
-If you have any questions, checkout our [documentation](https://docs.streamlit.io) and [community
-forums](https://discuss.streamlit.io).
-
-In the meantime, below is an example of what you can do with just a few lines of code:
-"""
-
-num_points = st.slider("Number of points in spiral", 1, 10000, 1100)
-num_turns = st.slider("Number of turns in spiral", 1, 300, 31)
-
-indices = np.linspace(0, 1, num_points)
-theta = 2 * np.pi * num_turns * indices
-radius = indices
-
-x = radius * np.cos(theta)
-y = radius * np.sin(theta)
-
-df = pd.DataFrame({
-    "x": x,
-    "y": y,
-    "idx": indices,
-    "rand": np.random.randn(num_points),
-})
-
-st.altair_chart(alt.Chart(df, height=700, width=700)
-    .mark_point(filled=True)
-    .encode(
-        x=alt.X("x", axis=None),
-        y=alt.Y("y", axis=None),
-        color=alt.Color("idx", legend=None, scale=alt.Scale()),
-        size=alt.Size("rand", legend=None, scale=alt.Scale(range=[1, 150])),
-    ))
+languages = ['American English','British English','Spanish','French','Italian']
+flags = ['🇺🇸','🇬🇧','🇪🇸','🇫🇷','🇮🇹']
+voices = ['af_heart','am_adam','bf_isabella','bm_lewis','ef_dora','em_alex','ff_siwis','if_sara','im_nicola']
+
+@st.cache_resource
+def model_setup(lang_code='a'):
+    return KPipeline(lang_code=lang_code)
+    
+### Title
+st.title("Convert your text into audio")
+st.subheader("with your options of language, speed and voice")
+
+# Text
+input_text = st.text_area(
+    "Your text:"
+)
+
+if input_text:
+    st.write(f"{len(input_text)} characters")
+    language = st.radio(
+        "Language:",
+        ['']+[flag+lang for flag,lang in zip(flags,languages)],
+    )
+
+    # Language
+    if language:
+        match language[2:]:
+            case 'American English':
+                lang_code = 'a'
+            case 'British English':
+                lang_code = 'b'
+            case 'Spanish':
+                lang_code = 'e'
+            case 'French':
+                lang_code = 'f'
+            case 'Italian':
+                lang_code = 'i'
+
+        # Speed
+        speed = st.radio(
+            "Speed:",
+            ['slow','normal','fast'],
+            index = 1
+        )
+        if speed == 'slow':
+            sp = 0.8
+        elif speed == 'normal':
+            sp = 1
+        elif speed == 'fast':
+            sp = 1.4
+
+        # Voice
+        voices_l = [voice for voice in voices if voice[0]==lang_code]
+        voices_gender = ['Female' if voice[1]=='f' else 'Male' for voice in voices_l]
+        voice = st.radio(
+            "Voice:",
+            ['']+voices_gender,
+        )
+        if voice:
+            if voice == 'Female':
+                voice = voices_l[0]
+            else:
+                voice = voices_l[1]
+                
+            pipeline = KPipeline(lang_code=lang_code)
+            generator = pipeline(input_text, voice=voice, speed=sp, split_pattern=r'')
+
+            for i,(_, _, audio) in enumerate(generator):
+                with tempfile.TemporaryDirectory() as temp_dir:
+                    sf.write(temp_dir+'temp.wav', audio, 24000)
+            st.audio(temp_dir+'temp.wav')