init space

.gitattributes

@@ -1,35 +1,35 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,13 +1,13 @@
----
-title: StyleTTS2 Lite Vi Space
-emoji: 🚀
-colorFrom: yellow
-colorTo: red
-sdk: gradio
-sdk_version: 5.25.0
-app_file: app.py
-pinned: false
-license: cc-by-nc-sa-4.0
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+---
+title: StyleTTS2 Lite Vi
+emoji: 🦀
+colorFrom: gray
+colorTo: pink
+sdk: gradio
+sdk_version: 5.24.0
+app_file: app.py
+pinned: false
+license: cc-by-nc-sa-4.0
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,96 @@
+import gradio as gr
+import subprocess
+import os
+import sys
+import soundfile as sf
+import numpy as np
+import torch.cuda
+
+repo_url = "https://huggingface.co/dangtr0408/StyleTTS2-lite-vi"
+repo_dir = "StyleTTS2-lite-vi"
+
+if not os.path.exists(repo_dir):
+    subprocess.run(["git", "clone", repo_url, repo_dir])
+
+# Clone repo and load model
+sys.path.append(os.path.abspath(repo_dir))
+from inference import StyleTTS2
+
+device = 'cuda' if torch.cuda.is_available() else 'cpu'
+
+config_path = os.path.join(repo_dir, "Models", "config.yml")
+models_path = os.path.join(repo_dir, "Models", "model_vi_en.pth")
+model = StyleTTS2(config_path, models_path).to(device)
+
+# Core inference function
+def process_inputs(text_prompt, reference_audio_paths,
+                   n_merge, randomness, smooth_dur,
+                   denoise, t_denoise, split_dur):
+    
+    speakers = {}
+    for i, path in enumerate(reference_audio_paths, 1):
+        speaker_id = f"id_{i}"
+        speakers[speaker_id] = {
+            "path": path,
+            "lang": "vi",
+            "speed": 1.1
+    }
+
+    # Synthesize audio
+    r = model.generate(
+        text_prompt, speakers, denoise, t_denoise,
+        split_dur, "[id_1]", n_merge, randomness, smooth_dur
+    )
+
+    r = r / np.abs(r).max()
+    sf.write("output.wav", r, samplerate=24000)
+    return "output.wav"
+
+custom_css = """
+    #custom-box {
+        min-height: 300px !important;
+        display: flex;
+        align-items: center;
+    }
+    #custom-box textarea {
+        min-height: 250px !important;
+        height: 100% !important;
+    }
+"""
+
+# Gradio UI
+with gr.Blocks(css=custom_css) as demo:
+    gr.Markdown("## StyleTTS2-lite-vi Demo")
+    gr.Markdown("Upload a reference audio and input your text to synthesize speech with style control.")
+
+    with gr.Row():
+        text_prompt = gr.Textbox(label="Text Prompt", placeholder="Enter your text here...", elem_id="custom-box")
+        reference_audios = gr.File(label="Reference Audios", file_types=[".wav", ".mp3", ".flac"], file_count="multiple", elem_id="custom-box")
+    # Parameters
+    with gr.Accordion("Advanced Settings", open=False):
+        denoise = gr.Checkbox(label="Apply Denoising", value=True)
+        t_denoise = gr.Slider(0.0, 1.0, value=0.3, label="Denoise Strength")
+        n_merge = gr.Slider(1, 30, value=16, label="Min Words to Merge")
+        randomness = gr.Slider(0.0, 1.0, value=0.2, label="Randomness")
+        smooth_dur = gr.Slider(0.0, 1.0, value=0.15, label="Smooth Duration")
+        split_dur = gr.Slider(0, 10, step=1, value=3, label="Split Ref Audio Duration")
+
+    submit_button = gr.Button("Synthesize")
+    synthesized_audio = gr.Audio(label="Synthesized Audio", type="filepath")
+
+    submit_button.click(
+        fn=process_inputs,
+        inputs=[
+            text_prompt,
+            reference_audios,
+            n_merge,
+            randomness,
+            smooth_dur,
+            denoise,
+            t_denoise,
+            split_dur
+        ],
+        outputs=synthesized_audio
+    )
+
+demo.launch()

packages.txt

@@ -0,0 +1 @@
+espeak-ng

requirements.txt

@@ -0,0 +1,10 @@
+torch
+torchaudio
+numpy
+PyYAML
+munch
+nltk
+librosa
+noisereduce
+phonemizer
+espeakng-loader