Duplicate from mesolitica/ms-tts-VITS

Co-authored-by: husein zolkepli <[email protected]>

.gitattributes

@@ -0,0 +1,33 @@
+*.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
+*.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
+*.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

@@ -0,0 +1,13 @@
+---
+title: E2E-TTS VITS
+emoji: 🦜
+colorFrom: pink
+colorTo: purple
+sdk: gradio
+sdk_version: 3.8.2
+app_file: app.py
+pinned: false
+duplicated_from: mesolitica/ms-tts-VITS
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,48 @@
+import os
+
+os.environ['CUDA_VISIBLE_DEVICES'] = ''
+os.environ['TF_FORCE_GPU_ALLOW_GROWTH'] = 'true'
+
+import malaya_speech
+from malaya_speech.utils.astype import float_to_int
+import gradio as gr
+import logging
+import json
+
+logging.basicConfig(level=logging.INFO)
+
+MODELS = {}
+AVAILABLE_MODELS = malaya_speech.tts.available_vits().index.tolist()
+
+def tts(text, model, temperature, length_ratio):
+    global MODELS
+    if model not in MODELS:
+        MODELS[model] = malaya_speech.tts.vits(model=model)
+    
+    r = MODELS[model].predict(
+        text, 
+        temperature = temperature,
+        length_ratio = length_ratio,
+    )
+    data = float_to_int(r['y'])
+    return (22050, data)
+
+demo = gr.Interface(
+    fn=tts,
+    inputs=[
+        gr.components.Textbox(label='Text'),
+        gr.components.Dropdown(label='Available models', choices=AVAILABLE_MODELS, value = 'mesolitica/VITS-osman'),
+        gr.Slider(0.0, 1.0, value=0.6666, label='temperature, changing this will manipulate pitch'),
+        gr.Slider(0.0, 3.0, value=1.0, label='length ratio, changing this will manipulate duration output'),
+    ],
+    outputs=['audio'],
+    examples=[
+        ['Syed Saddiq berkata, mereka seharusnya mengingati bahawa semasa menjadi Perdana Menteri Pakatan Harapan', 'mesolitica/VITS-osman', 0.6666, 1.0],
+        ['SHAH ALAM - Pertubuhan Kebajikan Anak Bersatu Selangor bersetuju pihak kerajaan mewujudkan Suruhanjaya Siasatan Diraja untuk menyiasat isu kartel daging.', 'mesolitica/VITS-haqkiem', 0.6666, 1.0],
+    ],
+    cache_examples=False,
+    title='End-to-End TTS using VITS from Mesolitica',
+)
+
+demo.launch(server_name='0.0.0.0')
+    

packages.txt

@@ -0,0 +1 @@
+libsndfile1

requirements.txt

@@ -0,0 +1,7 @@
+malaya-speech
+malaya
+tensorflow==2.9.2
+torch==1.12.1
+malaya-boilerplate==0.0.23
+matplotlib
+transformers