Merge master

.gitignore

@@ -166,7 +166,8 @@ cython_debug/
 filelists/*
 !/filelists/esd.list
 data/*
-/config.yml
+/*.yml
+!/default_config.yml
 /Web/
 /emotional/*/*.bin
 /bert/*/*.bin
@@ -176,5 +177,9 @@ data/*
 /bert/*/*.msgpack
 asr_transcript.py
 extract_list.py
+dataset
 /Data
+Model
+raw/
+logs/
 Data/*

.pre-commit-config.yaml

@@ -7,13 +7,13 @@ repos:
       - id: trailing-whitespace
 
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.1.3
+    rev: v0.1.7
     hooks:
       - id: ruff
         args: [ --fix ]
 
   - repo: https://github.com/psf/black
-    rev: 23.10.1
+    rev: 23.11.0
     hooks:
       - id: black
 

README.md

@@ -1,6 +1,14 @@
+<div align="center">
+
+<img alt="LOGO" src="https://cdn.jsdelivr.net/gh/fishaudio/fish-diffusion@main/images/logo_512x512.png" width="256" height="256" />
+
 # Bert-VITS2
 
-VITS2 Backbone with bert
+VITS2 Backbone with multilingual bert
+
+For quick guide, please refer to `webui_preprocess.py`.
+
+简易教程请参见 `webui_preprocess.py`。
 
 ## 请注意，本项目核心思路来源于[anyvoiceai/MassTTS](https://github.com/anyvoiceai/MassTTS) 一个非常好的tts项目
 ## MassTTS的演示demo为[ai版峰哥锐评峰哥本人,并找回了在金三角失落的腰子](https://www.bilibili.com/video/BV1w24y1c7z9)
@@ -16,6 +24,7 @@ VITS2 Backbone with bert
 ### 严禁用于任何政治相关用途。
 #### Video:https://www.bilibili.com/video/BV1hp4y1K78E
 #### Demo:https://www.bilibili.com/video/BV1TF411k78w
+#### QQ Group：815818430
 ## References
 + [anyvoiceai/MassTTS](https://github.com/anyvoiceai/MassTTS)
 + [jaywalnut310/vits](https://github.com/jaywalnut310/vits)
@@ -24,6 +33,7 @@ VITS2 Backbone with bert
 + [PaddlePaddle/PaddleSpeech](https://github.com/PaddlePaddle/PaddleSpeech)
 + [emotional-vits](https://github.com/innnky/emotional-vits)
 + [Bert-VITS2-en](https://github.com/xwan07017/Bert-VITS2-en)
++ [Bert-VITS2-UI](https://github.com/jiangyuxiaoxiao/Bert-VITS2-UI)
 ## 感谢所有贡献者作出的努力
 <a href="https://github.com/fishaudio/Bert-VITS2/graphs/contributors" target="_blank">
   <img src="https://contrib.rocks/image?repo=fishaudio/Bert-VITS2"/>

bert/bert_models.json

@@ -0,0 +1,14 @@
+{
+    "deberta-v2-large-japanese-char-wwm": {
+        "repo_id": "ku-nlp/deberta-v2-large-japanese-char-wwm",
+        "files": ["pytorch_model.bin"]
+    },
+    "chinese-roberta-wwm-ext-large": {
+        "repo_id": "hfl/chinese-roberta-wwm-ext-large",
+        "files": ["pytorch_model.bin"]
+    },
+    "deberta-v3-large": {
+        "repo_id": "microsoft/deberta-v3-large",
+        "files": ["spm.model", "pytorch_model.bin"]
+    }
+}

emotional/wav2vec2-large-robust-12-ft-emotion-msp-dim/.gitattributes → bert/deberta-v2-large-japanese-char-wwm/.gitattributes

@@ -1,28 +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
+*.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
-*.zstandard filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

bert/deberta-v2-large-japanese-char-wwm/README.md

@@ -0,0 +1,89 @@
+---
+language: ja
+license: cc-by-sa-4.0
+library_name: transformers
+tags:
+  - deberta
+  - deberta-v2
+  - fill-mask
+  - character
+  - wwm
+datasets:
+  - wikipedia
+  - cc100
+  - oscar
+metrics:
+  - accuracy
+mask_token: "[MASK]"
+widget:
+    - text: "京都大学で自然言語処理を[MASK][MASK]する。"
+---
+
+# Model Card for Japanese character-level DeBERTa V2 large
+
+## Model description
+
+This is a Japanese DeBERTa V2 large model pre-trained on Japanese Wikipedia, the Japanese portion of CC-100, and the Japanese portion of OSCAR.
+This model is trained with character-level tokenization and whole word masking.
+
+## How to use
+
+You can use this model for masked language modeling as follows:
+
+```python
+from transformers import AutoTokenizer, AutoModelForMaskedLM
+tokenizer = AutoTokenizer.from_pretrained('ku-nlp/deberta-v2-large-japanese-char-wwm')
+model = AutoModelForMaskedLM.from_pretrained('ku-nlp/deberta-v2-large-japanese-char-wwm')
+
+sentence = '京都大学で自然言語処理を[MASK][MASK]する。'
+encoding = tokenizer(sentence, return_tensors='pt')
+...
+```
+
+You can also fine-tune this model on downstream tasks.
+
+## Tokenization
+
+There is no need to tokenize texts in advance, and you can give raw texts to the tokenizer.
+The texts are tokenized into character-level tokens by [sentencepiece](https://github.com/google/sentencepiece).
+
+## Training data
+
+We used the following corpora for pre-training:
+
+- Japanese Wikipedia (as of 20221020, 3.2GB, 27M sentences, 1.3M documents)
+- Japanese portion of CC-100 (85GB, 619M sentences, 66M documents)
+- Japanese portion of OSCAR (54GB, 326M sentences, 25M documents)
+
+Note that we filtered out documents annotated with "header", "footer", or "noisy" tags in OSCAR.
+Also note that Japanese Wikipedia was duplicated 10 times to make the total size of the corpus comparable to that of CC-100 and OSCAR. As a result, the total size of the training data is 171GB.
+
+## Training procedure
+
+We first segmented texts in the corpora into words using [Juman++ 2.0.0-rc3](https://github.com/ku-nlp/jumanpp/releases/tag/v2.0.0-rc3) for whole word masking.
+Then, we built a sentencepiece model with 22,012 tokens including all characters that appear in the training corpus.
+
+We tokenized raw corpora into character-level subwords using the sentencepiece model and trained the Japanese DeBERTa model using [transformers](https://github.com/huggingface/transformers) library.
+The training took 26 days using 16 NVIDIA A100-SXM4-40GB GPUs.
+
+The following hyperparameters were used during pre-training:
+
+- learning_rate: 1e-4
+- per_device_train_batch_size: 26
+- distributed_type: multi-GPU
+- num_devices: 16
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 3,328
+- max_seq_length: 512
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-06
+- lr_scheduler_type: linear schedule with warmup (lr = 0 at 300k steps)
+- training_steps: 260,000
+- warmup_steps: 10,000
+
+The accuracy of the trained model on the masked language modeling task was 0.795.
+The evaluation set consists of 5,000 randomly sampled documents from each of the training corpora.
+
+## Acknowledgments
+
+This work was supported by Joint Usage/Research Center for Interdisciplinary Large-scale Information Infrastructures (JHPCN) through General Collaboration Project no. jh221004, "Developing a Platform for Constructing and Sharing of Large-Scale Japanese Language Models".
+For training models, we used the mdx: a platform for the data-driven future.

bert/deberta-v2-large-japanese-char-wwm/config.json

@@ -0,0 +1,37 @@
+{
+  "architectures": [
+    "DebertaV2ForMaskedLM"
+  ],
+  "attention_head_size": 64,
+  "attention_probs_dropout_prob": 0.1,
+  "conv_act": "gelu",
+  "conv_kernel_size": 3,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 1024,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float16",
+  "transformers_version": "4.25.1",
+  "type_vocab_size": 0,
+  "vocab_size": 22012
+}

bert/deberta-v2-large-japanese-char-wwm/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

bert/deberta-v2-large-japanese-char-wwm/tokenizer_config.json

@@ -0,0 +1,19 @@
+{
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "do_subword_tokenize": true,
+  "do_word_tokenize": true,
+  "jumanpp_kwargs": null,
+  "mask_token": "[MASK]",
+  "mecab_kwargs": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "subword_tokenizer_type": "character",
+  "sudachi_kwargs": null,
+  "tokenizer_class": "BertJapaneseTokenizer",
+  "unk_token": "[UNK]",
+  "word_tokenizer_type": "basic"
+}