fix emo

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin 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
+*.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
+*.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
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*.tfevents* filter=lfs diff=lfs merge=lfs -text
+*.db* filter=lfs diff=lfs merge=lfs -text
+*.ark* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,32 +1,25 @@
 ---
-
 # 详细文档见https://modelscope.cn/docs/%E5%88%9B%E7%A9%BA%E9%97%B4%E5%8D%A1%E7%89%87
-
 domain: #领域：cv/nlp/audio/multi-modal/AutoML
-
 # - cv
-
 tags: #自定义标签
 -
 datasets: #关联数据集
-evaluation:
-#- damotest/beans
-test:
-#- damotest/squad
-train:
-#- modelscope/coco_2014_caption
+ evaluation:
+ #- damotest/beans
+ test:
+ #- damotest/squad
+ train:
+ #- modelscope/coco_2014_caption
 models: #关联模型
 #- damo/speech_charctc_kws_phone-xiaoyunxiaoyun
 
 ## 启动文件(若SDK为Gradio/Streamlit，默认为app.py, 若为Static HTML, 默认为index.html)
-
 deployspec:
-entry_file: webui.py
+ entry_file: webui.py
 license: Apache License 2.0
 ---
-
 #### Clone with HTTP
-
 ```bash
  git clone https://www.modelscope.cn/studios/SpicyqSama007/Bert-VITS2-v2.3-clap.git
 ```

all_process.py

@@ -1196,8 +1196,8 @@ def fn_delete_folder(selected_folders):
  infer_ver_box = gr.Dropdown(
  label="更改推理版本",
  info="已经实现兼容推理，请选择合适的版本",
- choices=["2.2", "2.1", "2.0.2", "2.0.1", "2.0", "1.1.1", "1.1.0", "1.0.1"],
- value="2.2",
+ choices=["2.1", "2.0.2", "2.0.1", "2.0", "1.1.1", "1.1.0", "1.0.1"],
+ value="2.1",
  )
  with gr.Row():
  radio_webui_share = gr.Radio(

clap_gen.py

@@ -1,15 +1,15 @@
 import argparse
-import os
 from multiprocessing import Pool, cpu_count
 
-import librosa
 import torch
 import torch.multiprocessing as mp
 from tqdm import tqdm
 
 import utils
-from clap_wrapper import get_clap_audio_feature
 from config import config
+from clap_wrapper import get_clap_audio_feature
+import librosa
+import os
 
 os.environ["OMP_NUM_THREADS"] = "1"
 os.environ["MKL_NUM_THREADS"] = "1"

clap_wrapper.py

@@ -11,9 +11,9 @@
 
 def get_clap_audio_feature(audio_data, device=config.bert_gen_config.device):
  if (
-  sys.platform == "darwin"
-  and torch.backends.mps.is_available()
-  and device == "cpu"
+ sys.platform == "darwin"
+ and torch.backends.mps.is_available()
+ and device == "cpu"
  ):
  device = "mps"
  if not device:
@@ -32,9 +32,9 @@ def get_clap_audio_feature(audio_data, device=config.bert_gen_config.device):
 
 def get_clap_text_feature(text, device=config.bert_gen_config.device):
  if (
-  sys.platform == "darwin"
-  and torch.backends.mps.is_available()
-  and device == "cpu"
+ sys.platform == "darwin"
+ and torch.backends.mps.is_available()
+ and device == "cpu"
  ):
  device = "mps"
  if not device:

commons.py

@@ -1,5 +1,4 @@
 import math
-
 import torch
 from torch.nn import functional as F
 

compress_model.py

@@ -1,12 +1,11 @@
-import os
 from collections import OrderedDict
-
+from text.symbols import symbols
 import torch
 
+from tools.log import logger
 import utils
 from models import SynthesizerTrn
-from text.symbols import symbols
-from tools.log import logger
+import os
 
 
 def copyStateDict(state_dict):

config.py

@@ -2,12 +2,11 @@
 @Desc: 全局配置文件读取
 """
 import argparse
+import yaml
+from typing import Dict, List
 import os
 import shutil
 import sys
-from typing import Dict, List
-
-import yaml
 
 
 class Resample_config:
@@ -33,15 +32,15 @@ class Preprocess_text_config:
  """数据预处理配置"""
 
  def __init__(
-  self,
-  transcription_path: str,
-  cleaned_path: str,
-  train_path: str,
-  val_path: str,
-  config_path: str,
-  val_per_lang: int = 5,
-  max_val_total: int = 10000,
-  clean: bool = True,
+ self,
+ transcription_path: str,
+ cleaned_path: str,
+ train_path: str,
+ val_path: str,
+ config_path: str,
+ val_per_lang: int = 5,
+ max_val_total: int = 10000,
+ clean: bool = True,
  ):
  self.transcription_path: str = transcription_path # 原始文本文件路径，文本格式应为{wav_path}|{speaker_name}|{language}|{text}。
  self.cleaned_path: str = cleaned_path # 数据清洗后文本路径，可以不填。不填则将在原始文本目录生成
@@ -96,11 +95,11 @@ class Emo_gen_config:
  """emo_gen 配置"""
 
  def __init__(
-  self,
-  config_path: str,
-  num_processes: int = 2,
-  device: str = "cuda",
-  use_multi_device: bool = False,
+ self,
+ config_path: str,
+ num_processes: int = 2,
+ device: str = "cuda",
+ use_multi_device: bool = False,
  ):
  self.config_path = config_path
  self.num_processes = num_processes
@@ -248,4 +247,4 @@ def __init__(self, config_path: str):
 parser.add_argument("-y", "--yml_config", type=str, default="config.yml")
 args, _ = parser.parse_known_args()
 config = Config(args.yml_config)
-yml_config = args.yml_config
+yml_config = args.yml_config

configs/config.json

@@ -18,7 +18,10 @@
  "warmup_epochs": 0,
  "c_mel": 45,
  "c_kl": 1.0,
- "skip_optimizer": true
+ "skip_optimizer": true,
+ "freeze_ZH_bert": false,
+ "freeze_JP_bert": false,
+ "freeze_EN_bert": false
  },
  "data": {
  "training_files": "filelists/train.list",
@@ -946,5 +949,5 @@
  "use_spectral_norm": false,
  "gin_channels": 256
  },
- "version": "2.1"
+ "version": "2.2"
 }

data_utils.py

@@ -1,16 +1,15 @@
 import os
 import random
-
 import torch
 import torch.utils.data
 from tqdm import tqdm
-
+import numpy as np
+from tools.log import logger
 import commons
-from config import config
 from mel_processing import spectrogram_torch, mel_spectrogram_torch
-from text import cleaned_text_to_sequence
-from tools.log import logger
 from utils import load_wav_to_torch, load_filepaths_and_text
+from text import cleaned_text_to_sequence
+from config import config
 
 """Multi speaker version"""
 

emotional/clap-htsat-fused/.gitattributes

@@ -0,0 +1,34 @@
+*.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
+*.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