init

.gitattributes

@@ -1,31 +0,0 @@
-*.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
-*.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
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pb 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
-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

MANIFEST.in

@@ -0,0 +1,4 @@
+include assets/*
+include inputs/*
+include LICENSE
+include requirements.txt

README.md

@@ -1,13 +0,0 @@
----
-title: MockingBird
-emoji: 🏃
-colorFrom: red
-colorTo: green
-sdk: gradio
-sdk_version: 3.4
-app_file: app.py
-pinned: false
-license: mit
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,94 @@
+import os
+import gradio as gr
+from mockingbirdforuse import MockingBird
+from PIL import Image
+import torch
+from pathlib import Path
+from random import randint
+import sys
+from subprocess import call
+
+
+mockingbird = MockingBird()
+mockingbird_path = Path(os.path.dirname(__file__))
+base_url = "https://pan.yropo.top/source/mockingbird/"
+
+for sy in ["encoder.pt", "g_hifigan.pt"]:
+    if not os.path.exists(os.path.join(mockingbird_path, sy)):
+        torch.hub.download_url_to_file(f'{base_url}/{sy}', sy)
+
+for model in ["azusa", "nanmei", "ltyai", "tianyi"]:
+    model_path = mockingbird_path / model
+    model_path.mkdir(parents=True, exist_ok=True)
+    for file_name in ["record.wav", f"{model}.pt"]:
+        if not os.path.exists(os.path.join(model_path, file_name)):
+            torch.hub.download_url_to_file(f'{base_url}/{model}/{file_name}', model_path / file_name)
+  
+    
+def run_cmd(command):
+    try:
+        print(command)
+        call(command, shell=True)
+    except KeyboardInterrupt:
+        print("Process interrupted")
+        sys.exit(1)
+# run_cmd("wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.0/RealESRGAN_x4plus.pth -P .")
+# run_cmd("pip install basicsr")
+# run_cmd("pip freeze")
+
+# os.system("wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.2.4/RealESRGAN_x4plus_anime_6B.pth -P .")
+
+
+def inference(text, model_name: str):
+    model_path = mockingbird_path / model_name
+    mockingbird.load_model(
+        Path(os.path.join(mockingbird_path, "encoder.pt")),
+        Path(os.path.join(mockingbird_path, "g_hifigan.pt")),
+        # Path(os.path.join(mockingbird_path, "wavernn.pt"))
+    )
+    mockingbird.set_synthesizer(Path(os.path.join(model_path, f"{model_name}.pt")))
+    _id = randint(1, 10000)
+    # INPUT_DIR = "/tmp/input_image" + str(_id) + "/"
+    OUTPUT_DIR = "/tmp/" + str(_id) + "/"
+    # run_cmd("rm -rf " + INPUT_DIR)
+    run_cmd("rm -rf " + OUTPUT_DIR)
+    # run_cmd("mkdir " + INPUT_DIR)
+    run_cmd("mkdir " + OUTPUT_DIR)
+    # basewidth = 256
+    # wpercent = (basewidth/float(img.size[0]))
+    # hsize = int((float(img.size[1])*float(wpercent)))
+    # img = img.resize((basewidth,hsize), Image.ANTIALIAS)
+    # img.save(INPUT_DIR + "1.jpg", "JPEG")
+    record = mockingbird.synthesize(
+            str(text),
+            model_path / "record.wav",
+            "HifiGan",
+            0,
+            9,
+            1000,)
+    with open(os.path.join(OUTPUT_DIR, "result.wav"), 'wb') as file:
+        file.write(record.getvalue())
+    # if mode == "base":
+    #     run_cmd("python inference_realesrgan.py -n RealESRGAN_x4plus -i "+ INPUT_DIR + " -o " + OUTPUT_DIR)
+    # else:
+    #     os.system("python inference_realesrgan.py -n RealESRGAN_x4plus_anime_6B -i "+ INPUT_DIR + " -o " + OUTPUT_DIR)
+    return os.path.join(OUTPUT_DIR, "result.wav")
+
+
+
+        
+title = "MockingBird"
+description = "🚀AI拟声: 5秒内克隆您的声音并生成任意语音内容 Clone a voice in 5 seconds to generate arbitrary speech in real-time"
+article = "<a href='https://github.com/babysor/MockingBird'>Github Repo</a></p>"
+
+gr.Interface(
+    inference, 
+    [gr.inputs.Textbox(type="value", label="Input"),gr.inputs.Radio(["azusa", "nanmei", "ltyai", "tianyi"], type="value", default="azusa", label="model type")], 
+    gr.outputs.Audio(type="auto", label="Output"),
+    title=title,
+    description=description,
+    article=article,
+    examples=[
+    ['阿梓不是你的电子播放器','azusa'],
+    ['不是','nanmei']
+    ]).launch()

packages.txt

@@ -0,0 +1,3 @@
+ffmpeg 
+libsm6 
+libxext6 

requirements.txt

@@ -0,0 +1,18 @@
+torch
+numpy
+opencv-python-headless
+setuptools
+Pillow
+gradio
+torchvision
+addict
+future
+lmdb
+pyyaml
+requests
+scikit-image
+scipy
+tb-nightly
+tqdm
+yapf
+mockingbirdforuse