fix build error

.gitignore

@@ -0,0 +1,2 @@
+myenv
+venv

api.py

@@ -0,0 +1,76 @@
+import torch
+from fastapi import FastAPI
+from pydantic import BaseModel
+import numpy as np
+import base64
+import io
+from scipy.io.wavfile import write
+import sounddevice as sd
+
+# 自定义模块
+import commons
+import utils
+from models import SynthesizerTrn
+from text.symbols import symbols
+from text import text_to_sequence
+
+# 检查 PyTorch 版本
+print(torch.__version__)
+
+# 检查 CUDA 是否可用
+print(torch.cuda.is_available())
+
+# 检查当前 CUDA 版本
+print(torch.version.cuda)
+
+# FastAPI 应用
+app = FastAPI()
+
+# 请求体模型
+class TextRequest(BaseModel):
+    text: str
+
+# 加载配置和模型
+config_path = "configs/steins_gate_base.json"
+checkpoint_path = "G_265000.pth"
+hps = utils.get_hparams_from_file(config_path)
+net_g = SynthesizerTrn(
+    len(symbols),
+    hps.data.filter_length // 2 + 1,
+    hps.train.segment_size // hps.data.hop_length,
+    **hps.model,
+).eval()
+utils.load_checkpoint(checkpoint_path, net_g, None)
+
+# 文本到语音合成
+def text_to_speech(content):
+    stn_tst = text_to_sequence(content, hps.data.text_cleaners)
+    if hps.data.add_blank:
+        stn_tst = commons.intersperse(stn_tst, 0)
+    stn_tst = torch.LongTensor(stn_tst)
+    with torch.no_grad():
+        x_tst = stn_tst.unsqueeze(0)
+        x_tst_lengths = torch.LongTensor([stn_tst.size(0)])
+        audio = net_g.infer(x_tst, x_tst_lengths, noise_scale=0.667, noise_scale_w=0.8, length_scale=1)[0][0, 0].data.float().numpy()
+
+    return hps.data.sampling_rate, audio
+
+# API 路由：文本转语音
+@app.post("/synthesize")
+def synthesize(request: TextRequest):
+    # 假设 text_to_speech 是生成音频的函数
+    sampling_rate, audio = text_to_speech(request.text)
+
+    # 将音频数据保存到 BytesIO 对象
+    wav_bytes = io.BytesIO()
+    write(wav_bytes, sampling_rate, (audio * 32767).astype(np.int16))
+    wav_bytes.seek(0)  # 将指针移动到文件开头
+
+    # 将 WAV 文件编码为 Base64
+    audio_base64 = base64.b64encode(wav_bytes.read()).decode("utf-8")
+    return {"audio": audio_base64}
+
+# 主函数
+if __name__ == "__main__":
+    import uvicorn
+    uvicorn.run(app, host="127.0.0.1", port=8000)

api_example.py

@@ -0,0 +1,47 @@
+import requests
+import json
+import base64
+import io
+import sounddevice as sd
+import soundfile as sf
+
+# API 地址
+url = "http://127.0.0.1:8000/synthesize"
+
+# 请求体
+payload = {"text": "Hello, world!"}
+
+# 请求头
+headers = {"Content-Type": "application/json"}
+
+# 发送 POST 请求
+try:
+    print("Sending request to the API...")
+    response = requests.post(url, data=json.dumps(payload), headers=headers)
+    response.raise_for_status()  # 检查请求是否成功
+    result = response.json()
+    print("Response received.")
+
+    # 检查返回的音频数据
+    if "audio" in result:
+        print("Audio data received as Base64.")
+
+        # 解码 Base64 音频数据
+        audio_base64 = result["audio"]
+        audio_bytes = base64.b64decode(audio_base64)
+
+        # 使用 soundfile 直接从内存中读取音频数据
+        try:
+            audio_data, samplerate = sf.read(io.BytesIO(audio_bytes))
+            print(f"Playing audio (sample rate: {samplerate} Hz)...")
+            sd.play(audio_data, samplerate)
+            sd.wait()  # 等待播放完成
+            print("Audio playback finished.")
+        except sf.LibsndfileError as e:
+            print(f"Error reading audio data: {e}")
+    else:
+        print("Unexpected response format. No audio data found.")
+except requests.exceptions.RequestException as e:
+    print(f"Request failed: {e}")
+except Exception as e:
+    print(f"An error occurred: {e}")

app.py

@@ -1,25 +1,11 @@
-
-
-
-
-import os
-os.system('cd monotonic_align && python setup.py build_ext --inplace && cd ..')
-import gradio as gr
-
-import matplotlib.pyplot as plt
-import IPython.display as ipd
-
 import os
-import json
-import math
-import torch
-from torch import nn
-from torch.nn import functional as F
-from torch.utils.data import DataLoader
+import subprocess
 import logging
+import torch
+import gradio as gr
+from scipy.io.wavfile import write
 
-numba_logger = logging.getLogger('numba')
-numba_logger.setLevel(logging.WARNING)
+# 自定义模块
 import commons
 import utils
 from data_utils import TextAudioLoader, TextAudioCollate, TextAudioSpeakerLoader, TextAudioSpeakerCollate
@@ -27,44 +13,111 @@ from models import SynthesizerTrn
 from text.symbols import symbols
 from text import text_to_sequence
 
-from scipy.io.wavfile import write
-
-
-def get_text(text, hps):
-    text_norm = text_to_sequence(text, hps.data.text_cleaners)
-    if hps.data.add_blank:
-        text_norm = commons.intersperse(text_norm, 0)
-    text_norm = torch.LongTensor(text_norm)
-    return text_norm
-
-hps = utils.get_hparams_from_file("configs/steins_gate_base.json")
-
-net_g = SynthesizerTrn(
-    len(symbols),
-    hps.data.filter_length // 2 + 1,
-    hps.train.segment_size // hps.data.hop_length,
-    **hps.model)
-_ = net_g.eval()
-
-_ = utils.load_checkpoint("G_265000.pth", net_g, None)
-
-def syn(content):
-  stn_tst = get_text(content, hps)
-  with torch.no_grad():
-      x_tst = stn_tst.unsqueeze(0)
-      x_tst_lengths = torch.LongTensor([stn_tst.size(0)])
-      audio = net_g.infer(x_tst, x_tst_lengths, noise_scale=.667, noise_scale_w=0.8, length_scale=1)[0][0,0].data.float().numpy()
-  return (hps.data.sampling_rate,audio)
-  #ipd.display(ipd.Audio(audio, rate=hps.data.sampling_rate))
-
-
-app = gr.Blocks()
-with app:
-    with gr.Tabs():
-        with gr.TabItem("Basic"):
-            input1 = gr.Textbox()
-            submit = gr.Button("Convert", variant="primary")
-            output1 = gr.Audio(label="Output Audio")
-        submit.click(syn,input1,output1)
-        
-app.launch()
+# 配置日志
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
+
+# 编译 monotonic_align 模块
+def compile_monotonic_align():
+    try:
+
+        os.system('cd monotonic_align && python setup.py build_ext --inplace && cd ..')
+
+        logger.info("Successfully compiled monotonic_align.")
+    except subprocess.CalledProcessError as e:
+        logger.error(f"Failed to compile monotonic_align: {e}")
+        raise RuntimeError("Compilation of monotonic_align failed.")
+
+# 加载配置和模型
+def load_config_and_model(config_path, checkpoint_path):
+    if not os.path.exists(config_path):
+        raise FileNotFoundError(f"Config file not found: {config_path}")
+    if not os.path.exists(checkpoint_path):
+        raise FileNotFoundError(f"Checkpoint file not found: {checkpoint_path}")
+
+    # 加载超参数
+    hps = utils.get_hparams_from_file(config_path)
+    logger.info("Loaded hyperparameters from config file.")
+
+    # 初始化模型
+    net_g = SynthesizerTrn(
+        len(symbols),
+        hps.data.filter_length // 2 + 1,
+        hps.train.segment_size // hps.data.hop_length,
+        **hps.model,
+    )
+    net_g.eval()
+    logger.info("Initialized SynthesizerTrn model.")
+
+    # 加载预训练权重
+    utils.load_checkpoint(checkpoint_path, net_g, None)
+    logger.info(f"Loaded model checkpoint from {checkpoint_path}.")
+
+    return hps, net_g
+
+# 文本到语音合成
+def text_to_speech(content, hps, net_g):
+    if not content or not isinstance(content, str):
+        raise ValueError("Input text is empty or invalid.")
+
+    try:
+        # 将文本转换为序列
+        stn_tst = text_to_sequence(content, hps.data.text_cleaners)
+        if hps.data.add_blank:
+            stn_tst = commons.intersperse(stn_tst, 0)
+        stn_tst = torch.LongTensor(stn_tst)
+
+        # 模型推理
+        with torch.no_grad():
+            x_tst = stn_tst.unsqueeze(0)
+            x_tst_lengths = torch.LongTensor([stn_tst.size(0)])
+            audio = net_g.infer(
+                x_tst, x_tst_lengths, noise_scale=0.667, noise_scale_w=0.8, length_scale=1
+            )[0][0, 0].data.float().numpy()
+
+        return hps.data.sampling_rate, audio
+    except Exception as e:
+        logger.error(f"Error during text-to-speech synthesis: {e}")
+        raise RuntimeError("Failed to generate audio.")
+
+# Gradio 界面
+def create_gradio_interface(hps, net_g):
+    def safe_syn(content):
+        try:
+            return text_to_speech(content, hps, net_g)
+        except Exception as e:
+            logger.error(f"Error in Gradio interface: {e}")
+            return None
+
+    app = gr.Blocks()
+    with app:
+        with gr.Tabs():
+            with gr.TabItem("Basic"):
+                input1 = gr.Textbox(label="Input Text", placeholder="Enter text here...")
+                submit = gr.Button("Convert", variant="primary")
+                output1 = gr.Audio(label="Output Audio")
+            submit.click(safe_syn, input1, output1)
+
+    return app
+
+# 主函数
+def main():
+    try:
+        # 编译 monotonic_align
+        compile_monotonic_align()
+
+        # 加载配置和模型
+        config_path = "configs/steins_gate_base.json"
+        checkpoint_path = "G_265000.pth"
+        hps, net_g = load_config_and_model(config_path, checkpoint_path)
+
+        # 创建 Gradio 界面
+        app = create_gradio_interface(hps, net_g)
+        logger.info("Starting Gradio interface...")
+        app.launch()
+    except Exception as e:
+        logger.critical(f"Fatal error: {e}")
+        exit(1)
+
+if __name__ == "__main__":
+    main()

monotonic_align/.gitignore

@@ -0,0 +1,161 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+.vscode/

monotonic_align/LICENSE.md

@@ -0,0 +1,22 @@
+MIT License
+
+Copyright (c) 2023 Moonsik Park
+Copyright (c) 2021 Jaehyeon Kim
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

monotonic_align/PKG-INFO

@@ -0,0 +1,32 @@
+Metadata-Version: 2.1
+Name: monotonic_align
+Version: 1.0.0
+Summary: Monotonic Alignment Search module
+Author-email: Moonsik Park <[email protected]>
+Project-URL: repository, https://github.com/moonsikpark/monotonic_align
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Cython
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.7
+Description-Content-Type: text/markdown
+License-File: LICENSE.md
+
+# Monotonic Alignment Search
+
+This module does Monotonic Alignment Search required by the [Vits](https://github.com/jaywalnut310/vits) TTS model, and has been copied from [this source](https://github.com/jaywalnut310/vits/tree/2b91ceff252082644bd507d13476a49ea260cadf/monotonic_align).
+
+The module have been packaged properly as per [PEP 621](https://peps.python.org/pep-0621/), and has a binary distrubution compiled to nearly every UNIX environment.
+
+## License
+
+Please note that the author(s) are not liable for any claim, damages or other liability thereof.
+
+```
+MIT License
+
+Copyright (c) 2023 Moonsik Park
+Copyright (c) 2021 Jaehyeon Kim
+````

monotonic_align/README.md

@@ -0,0 +1,16 @@
+# Monotonic Alignment Search
+
+This module does Monotonic Alignment Search required by the [Vits](https://github.com/jaywalnut310/vits) TTS model, and has been copied from [this source](https://github.com/jaywalnut310/vits/tree/2b91ceff252082644bd507d13476a49ea260cadf/monotonic_align).
+
+The module have been packaged properly as per [PEP 621](https://peps.python.org/pep-0621/), and has a binary distrubution compiled to nearly every UNIX environment.
+
+## License
+
+Please note that the author(s) are not liable for any claim, damages or other liability thereof.
+
+```
+MIT License
+
+Copyright (c) 2023 Moonsik Park
+Copyright (c) 2021 Jaehyeon Kim
+````

monotonic_align/__init__.py

@@ -1,19 +0,0 @@
-import numpy as np
-import torch
-from .monotonic_align.core import maximum_path_c
-
-
-def maximum_path(neg_cent, mask):
-  """ Cython optimized version.
-  neg_cent: [b, t_t, t_s]
-  mask: [b, t_t, t_s]
-  """
-  device = neg_cent.device
-  dtype = neg_cent.dtype
-  neg_cent = neg_cent.data.cpu().numpy().astype(np.float32)
-  path = np.zeros(neg_cent.shape, dtype=np.int32)
-
-  t_t_max = mask.sum(1)[:, 0].data.cpu().numpy().astype(np.int32)
-  t_s_max = mask.sum(2)[:, 0].data.cpu().numpy().astype(np.int32)
-  maximum_path_c(path, neg_cent, t_t_max, t_s_max)
-  return torch.from_numpy(path).to(device=device, dtype=dtype)

monotonic_align/pyproject.toml

@@ -0,0 +1,33 @@
+[build-system]
+requires = ["setuptools==67.4.0", "setuptools-scm[toml]==7.1.0", "Cython==0.29.33"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "monotonic_align"
+authors = [
+    {name = "Moonsik Park", email = "[email protected]"},
+]
+description = "Monotonic Alignment Search module"
+readme = "README.md"
+requires-python = ">=3.7"
+classifiers = [
+    "Development Status :: 5 - Production/Stable",
+    "License :: OSI Approved :: MIT License",
+    "Operating System :: OS Independent",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Cython",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence",
+]
+dynamic = ["version"]
+
+
+[project.urls]
+repository = "https://github.com/moonsikpark/monotonic_align"
+
+[tool.setuptools]
+include-package-data = false
+
+[tool.setuptools_scm]
+
+[tool.setuptools.packages.find]
+where = ["src"]

monotonic_align/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

monotonic_align/setup.py

@@ -1,9 +1,10 @@
-from distutils.core import setup
-from Cython.Build import cythonize
-import numpy
+from setuptools import Extension, setup
 
 setup(
-  name = 'monotonic_align',
-  ext_modules = cythonize("core.pyx"),
-  include_dirs=[numpy.get_include()]
+    ext_modules=[
+        Extension(
+            name="monotonic_align.core",
+            sources=["src/core.pyx"],
+        ),
+    ]
 )

monotonic_align/{core.pyx → src/core.pyx}

@@ -1,3 +1,4 @@
+#cython: language_level=3
 cimport cython
 from cython.parallel import prange
 

requirements.txt

@@ -1,16 +1,20 @@
-Cython==0.29.21
-librosa==0.8.0
-matplotlib==3.3.1
-numpy==1.21.6
-phonemizer==2.2.1
-scipy==1.5.2
-tensorboard==2.3.0
+Cython
+librosa
+matplotlib
+numpy
+phonemizer
+scipy
+tensorboard
 torch
 torchvision
-Unidecode==1.1.1
-jamo==0.4.1
-pypinyin==0.44.0
-jieba==0.42.1
-cn2an==0.5.17
+Unidecode
+jamo
+pypinyin
+jieba
+cn2an
 IPython
-pyopenjtalk==0.2.0
+pyopenjtalk
+
+Pillow
+Cython
+gradio

utils.py

@@ -18,6 +18,8 @@ logger = logging
 def load_checkpoint(checkpoint_path, model, optimizer=None):
   assert os.path.isfile(checkpoint_path)
   checkpoint_dict = torch.load(checkpoint_path, map_location='cpu')
+  #checkpoint_dict = torch.load(checkpoint_path, map_location='cuda:0', weights_only=True)
+
   iteration = checkpoint_dict['iteration']
   learning_rate = checkpoint_dict['learning_rate']
   if optimizer is not None:
@@ -85,7 +87,7 @@ def plot_spectrogram_to_numpy(spectrogram):
     mpl_logger.setLevel(logging.WARNING)
   import matplotlib.pylab as plt
   import numpy as np
-  
+
   fig, ax = plt.subplots(figsize=(10,2))
   im = ax.imshow(spectrogram, aspect="auto", origin="lower",
                   interpolation='none')
@@ -147,7 +149,7 @@ def get_hparams(init=True):
                       help='JSON file for configuration')
   parser.add_argument('-m', '--model', type=str, required=True,
                       help='Model name')
-  
+
   args = parser.parse_args()
   model_dir = os.path.join("../drive/MyDrive", args.model)
 
@@ -165,7 +167,7 @@ def get_hparams(init=True):
     with open(config_save_path, "r") as f:
       data = f.read()
   config = json.loads(data)
-  
+
   hparams = HParams(**config)
   hparams.model_dir = model_dir
   return hparams
@@ -215,7 +217,7 @@ def get_logger(model_dir, filename="train.log"):
   global logger
   logger = logging.getLogger(os.path.basename(model_dir))
   logger.setLevel(logging.DEBUG)
-  
+
   formatter = logging.Formatter("%(asctime)s\t%(name)s\t%(levelname)s\t%(message)s")
   if not os.path.exists(model_dir):
     os.makedirs(model_dir)
@@ -232,7 +234,7 @@ class HParams():
       if type(v) == dict:
         v = HParams(**v)
       self[k] = v
-    
+
   def keys(self):
     return self.__dict__.keys()