feat: Add optimized model

app.py

@@ -5,10 +5,18 @@ import soundfile as sf
 from models import Tokenizer, Kokoro
 
 # Function to fetch available style vectors dynamically
+
+
 def get_style_vector_choices(directory="voices"):
     return [file for file in os.listdir(directory) if file.endswith(".pt")]
 
+
+def get_onnx_models(directory="weights"):
+    return [file for file in os.listdir(directory) if file.endswith(".onnx")]
+
 # Function to perform TTS using your local model
+
+
 def local_tts(
         text: str,
         model_path: str,
@@ -20,6 +28,8 @@ def local_tts(
         try:
             tokenizer = Tokenizer()
             style_vector_path = os.path.join("voices", style_vector)
+            model_path = os.path.join("weights", model_path)
+
             inference = Kokoro(model_path, style_vector_path, tokenizer=tokenizer, lang='en-us')
 
             audio, sample_rate = inference.generate_audio(text, speed=speed)
@@ -35,10 +45,12 @@ def local_tts(
     else:
         raise gr.Error("Input text cannot be empty.")
 
+
 # Get the list of available style vectors
 style_vector_choices = get_style_vector_choices()
+onnx_models_choices = get_onnx_models()
 
-# sample texts and their corresponding audio 
+# sample texts and their corresponding audio
 sample_outputs = [
     ("Educational Note", "Machine learning models rely on large datasets and complex algorithms to identify patterns and make predictions.", "assets/edu_note.wav"),
     ("Fun Fact", "Did you know that honey never spoils? Archaeologists have found pots of honey in ancient Egyptian tombs that are over 3,000 years old and still edible!", "assets/fun_fact.wav"),
@@ -54,10 +66,10 @@ example_texts = [
 # Gradio Interface
 with gr.Blocks() as demo:
     gr.Markdown("# <center> Kokoro-82m Text-to-Speech with Gradio </center>")
-    
+
     # Model-specific inputs
     with gr.Row(variant="panel"):
-        model_path = gr.Textbox(label="Model Path", value="weights/kokoro-v0_19.onnx", interactive=False)
+        model_path = gr.Dropdown(choices=onnx_models_choices, label="ONNX Model Path", value=onnx_models_choices[0])
         style_vector = gr.Dropdown(choices=style_vector_choices, label="Style Vector", value=style_vector_choices[0])
         output_file_format = gr.Dropdown(choices=["wav", "mp3"], label="Output Format", value="wav")
         speed = gr.Slider(minimum=0.5, maximum=2.0, value=1.0, step=0.1, label="Speed")
@@ -76,20 +88,19 @@ with gr.Blocks() as demo:
         inputs=[text, model_path, style_vector, output_file_format, speed],
         outputs=output_audio
     )
-    
+
     # Add example texts
     gr.Examples(
         examples=example_texts,
         inputs=[text],
         label="Click an example to populate the input text"
     )
-    
+
     # Add example texts and audios
     gr.Markdown("### Sample Texts and Audio")
     for topic, sample_text, sample_audio in sample_outputs:
         with gr.Row():
             gr.Textbox(value=sample_text, label=topic, interactive=False)
             gr.Audio(value=sample_audio, label="Example Audio", type="filepath", interactive=False)
-            
 
 demo.launch(server_name="0.0.0.0")

weights/kokoro-quant.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d7fe30313cc305d3290aafc748ac02a28f93cabd76702bdb1c5ebea496d4cad
+size 177465355