Merge pull request #141 from myshell-ai/dev-0219

Dev 0219

.gitignore

@@ -6,3 +6,6 @@ checkpoints
 trash
 examples*
 .env
+build
+*.egg-info/
+*.zip

demo_part1.ipynb

@@ -17,8 +17,8 @@
    "source": [
     "import os\n",
     "import torch\n",
-    "import se_extractor\n",
-    "from api import BaseSpeakerTTS, ToneColorConverter"
+    "from openvoice import se_extractor\n",
+    "from openvoice.api import BaseSpeakerTTS, ToneColorConverter"
    ]
   },
   {

demo_part2.ipynb

@@ -17,8 +17,8 @@
    "source": [
     "import os\n",
     "import torch\n",
-    "import se_extractor\n",
-    "from api import ToneColorConverter"
+    "from openvoice import se_extractor\n",
+    "from openvoice.api import ToneColorConverter"
    ]
   },
   {

docs/USAGE.md

@@ -49,7 +49,7 @@ conda install pytorch==1.13.1 torchvision==0.14.1 torchaudio==0.13.1 pytorch-cud
 pip install -r requirements.txt
 ```
 
-Download the checkpoint from [here](https://myshell-public-repo-hosting.s3.amazonaws.com/checkpoints_1226.zip) and extract it to the `checkpoints` folder
+Download the checkpoint from [here](https://myshell-public-repo-hosting.s3.amazonaws.com/openvoice/checkpoints_1226.zip) and extract it to the `checkpoints` folder
 
 **1. Flexible Voice Style Control.**
 Please see [`demo_part1.ipynb`](../demo_part1.ipynb) for an example usage of how OpenVoice enables flexible style control over the cloned voice.

openvoice/api.py

@@ -2,13 +2,13 @@ import torch
 import numpy as np
 import re
 import soundfile
-import utils
-import commons
+from openvoice import utils
+from openvoice import commons
 import os
 import librosa
-from text import text_to_sequence
-from mel_processing import spectrogram_torch
-from models import SynthesizerTrn
+from openvoice.text import text_to_sequence
+from openvoice.mel_processing import spectrogram_torch
+from openvoice.models import SynthesizerTrn
 
 
 class OpenVoiceBaseClass(object):

openvoice/attentions.py

@@ -3,7 +3,7 @@ import torch
 from torch import nn
 from torch.nn import functional as F
 
-import commons
+from openvoice import commons
 import logging
 
 logger = logging.getLogger(__name__)

openvoice/models.py

@@ -3,14 +3,14 @@ import torch
 from torch import nn
 from torch.nn import functional as F
 
-import commons
-import modules
-import attentions
+from openvoice import commons
+from openvoice import modules
+from openvoice import attentions
 
 from torch.nn import Conv1d, ConvTranspose1d, Conv2d
 from torch.nn.utils import weight_norm, remove_weight_norm, spectral_norm
 
-from commons import init_weights, get_padding
+from openvoice.commons import init_weights, get_padding
 
 
 class TextEncoder(nn.Module):

openvoice/modules.py

@@ -6,10 +6,10 @@ from torch.nn import functional as F
 from torch.nn import Conv1d
 from torch.nn.utils import weight_norm, remove_weight_norm
 
-import commons
-from commons import init_weights, get_padding
-from transforms import piecewise_rational_quadratic_transform
-from attentions import Encoder
+from openvoice import commons
+from openvoice.commons import init_weights, get_padding
+from openvoice.transforms import piecewise_rational_quadratic_transform
+from openvoice.attentions import Encoder
 
 LRELU_SLOPE = 0.1
 

openvoice/openvoice_app.py

@@ -4,8 +4,8 @@ import argparse
 import gradio as gr
 from zipfile import ZipFile
 import langid
-import se_extractor
-from api import BaseSpeakerTTS, ToneColorConverter
+from openvoice import se_extractor
+from openvoice.api import BaseSpeakerTTS, ToneColorConverter
 
 parser = argparse.ArgumentParser()
 parser.add_argument("--share", action='store_true', default=False, help="make link public")

openvoice/text/__init__.py

@@ -1,6 +1,6 @@
 """ from https://github.com/keithito/tacotron """
-from text import cleaners
-from text.symbols import symbols
+from openvoice.text import cleaners
+from openvoice.text.symbols import symbols
 
 
 # Mappings from symbol to numeric ID and vice versa:
@@ -43,7 +43,7 @@ def cleaned_text_to_sequence(cleaned_text, symbols):
 
 
 
-from text.symbols import language_tone_start_map
+from openvoice.text.symbols import language_tone_start_map
 def cleaned_text_to_sequence_vits2(cleaned_text, tones, language, symbols, languages):
     """Converts a string of text to a sequence of IDs corresponding to the symbols in the text.
     Args:

openvoice/text/cleaners.py

@@ -1,6 +1,6 @@
 import re
-from text.english import english_to_lazy_ipa, english_to_ipa2, english_to_lazy_ipa2
-from text.mandarin import number_to_chinese, chinese_to_bopomofo, latin_to_bopomofo, chinese_to_romaji, chinese_to_lazy_ipa, chinese_to_ipa, chinese_to_ipa2
+from openvoice.text.english import english_to_lazy_ipa, english_to_ipa2, english_to_lazy_ipa2
+from openvoice.text.mandarin import number_to_chinese, chinese_to_bopomofo, latin_to_bopomofo, chinese_to_romaji, chinese_to_lazy_ipa, chinese_to_ipa, chinese_to_ipa2
 
 def cjke_cleaners2(text):
     text = re.sub(r'\[ZH\](.*?)\[ZH\]',

setup.py

@@ -0,0 +1,45 @@
+from setuptools import setup
+
+setup(name='MyShell-OpenVoice',
+      version='0.0.0',
+      description='Instant voice cloning by MyShell.',
+      long_description=open('README.md').read().strip(),
+      long_description_content_type='text/markdown',
+      keywords=[
+            'text-to-speech',
+            'tts',
+            'voice-clone',
+            'zero-shot-tts'
+      ],
+      url='https://github.com/myshell-ai/OpenVoice',
+      project_urls={
+        'Documentation': 'https://github.com/myshell-ai/OpenVoice/blob/main/docs/USAGE.md',
+        'Changes': 'https://github.com/myshell-ai/OpenVoice/releases',
+        'Code': 'https://github.com/myshell-ai/OpenVoice',
+        'Issue tracker': 'https://github.com/myshell-ai/OpenVoice/issues',
+      },
+      author='MyShell',
+      author_email='ethan@myshell.ai',
+      license='Creative Commons Attribution-NonCommercial 4.0 International Public License',
+      packages=[
+          'openvoice'
+      ],
+      python_requires='>=3.9',
+      install_requires=[
+            'librosa==0.9.1',
+            'faster-whisper==0.9.0',
+            'pydub==0.25.1',
+            'wavmark==0.0.2',
+            'numpy==1.22.0',
+            'eng_to_ipa==0.0.2',
+            'inflect==7.0.0',
+            'unidecode==1.3.7',
+            'whisper-timestamped==1.14.2',
+            'pypinyin==0.50.0',
+            'cn2an==0.5.22',
+            'jieba==0.42.1',
+            'gradio==3.48.0',
+            'langid==1.1.6'
+      ],
+      zip_safe=False
+      )