Dev 2.3. (#242)

* Fix inputs of duration discriminator

* Add LSTM

* Update models.py

* Update tensorboard scalar

* Noise injection for minimizing modality gap

* Update infer.py

* support bf16 run

* del unused_para flag

* support bf16 config

* add grad clip

* fix(logger and grad):add dur grad,fix grad clip

* Update webui_preprocess.py

* Fix English G2P

* fix(bert_gen):add pass

* Pass SDP to DD

* Update webui_preprocess.py

* Update config.json

* Update webui.py

* Update chinese_bert.py

* Upload webui for deploy

* Update webui.py

* torch.save as pt not npy

* Update config.json

* add freeze emo vq

* Update webui_preprocess.py

* Fix tone_sandhi.py

* Comment up grad clip

* Fix in-place addition

* Add SLM discriminator

* Add DDP for WD

* Feat: Style text: make emotions and style similar to the style text by mixing bert (#240) (#241)

* fix:(oldVersion210) Load on demand Emotion model

* feat: update fastapi.py. 添加更多错误日志信息

* Switch pyopenjtalk to pyopenjtalk-prebuilt

* fix: update fastapi.py. 2.2 reference适配

* Update resample.py

* 修复Onnx导出的BUG (#237)

* Add files via upload

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Add files via upload

* Add files via upload

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Delete attentions_onnx.py

* Delete models_onnx.py

* Add files via upload

* Add files via upload

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Update __init__.py

* Update __init__.py

* Update __init__.py

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

---------



* Fix onnx

* Format export

* Feat: style-text and bert mixing (JA only)

* Ensure the same tensor shape

* Update

* update gradio version

* Fix

* Style text for chinese and english (ver 2.2)

* Style text for chinese and english (ver 2.1)

* Style text in FastAPI

* Translate style text desc in chinese

---------

Co-authored-by: litagin02 <[email protected]>
Co-authored-by: Sora <[email protected]>
Co-authored-by: Sihan Wang <[email protected]>
Co-authored-by: Ναρουσέ·μ·γιουμεμί·Χινακάννα <[email protected]>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

* Remove CLAP

* Revert "Remove CLAP"

This reverts commit 62fd59b.

Revert

* Remove CLAP

* bf16 audo grad cilp

* Update webui and infer utils

* Update webui.py

* Update webui.py

* Update webui-preprocess.py

* Update webui_preprocess.py

---------

Co-authored-by: Sihan Wang <[email protected]>
Co-authored-by: OedoSoldier <[email protected]>
Co-authored-by: litagin02 <[email protected]>
Co-authored-by: Sora <[email protected]>
Co-authored-by: Ναρουσέ·μ·γιουμεμί·Χινακάννα <[email protected]>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

Author: 6 people

.gitignore

@@ -170,6 +170,7 @@ data/*
 !/default_config.yml
 /Web/
 /emotional/*/*.bin
+/slm/*/*.bin
 /bert/*/*.bin
 /bert/*/*.h5
 /bert/*/*.model

bert_gen.py

@@ -1,17 +1,16 @@
-import argparse
-from multiprocessing import Pool, cpu_count
-
 import torch
-import torch.multiprocessing as mp
-from tqdm import tqdm
-
+from multiprocessing import Pool
 import commons
 import utils
+from tqdm import tqdm
+from text import check_bert_models, cleaned_text_to_sequence, get_bert
+import argparse
+import torch.multiprocessing as mp
 from config import config
-from text import cleaned_text_to_sequence, get_bert
 
 
-def process_line(line):
+def process_line(x):
+    line, add_blank = x
     device = config.bert_gen_config.device
     if config.bert_gen_config.use_multi_device:
         rank = mp.current_process()._identity
@@ -28,12 +27,13 @@ def process_line(line):
     word2ph = [i for i in word2ph]
     phone, tone, language = cleaned_text_to_sequence(phone, tone, language_str)
 
-    phone = commons.intersperse(phone, 0)
-    tone = commons.intersperse(tone, 0)
-    language = commons.intersperse(language, 0)
-    for i in range(len(word2ph)):
-        word2ph[i] = word2ph[i] * 2
-    word2ph[0] += 1
+    if add_blank:
+        phone = commons.intersperse(phone, 0)
+        tone = commons.intersperse(tone, 0)
+        language = commons.intersperse(language, 0)
+        for i in range(len(word2ph)):
+            word2ph[i] = word2ph[i] * 2
+        word2ph[0] += 1
 
     bert_path = wav_path.replace(".WAV", ".wav").replace(".wav", ".bert.pt")
 
@@ -59,16 +59,23 @@ def process_line(line):
     args, _ = parser.parse_known_args()
     config_path = args.config
     hps = utils.get_hparams_from_file(config_path)
+    check_bert_models()
     lines = []
     with open(hps.data.training_files, encoding="utf-8") as f:
         lines.extend(f.readlines())
 
     with open(hps.data.validation_files, encoding="utf-8") as f:
         lines.extend(f.readlines())
+    add_blank = [hps.data.add_blank] * len(lines)
+
     if len(lines) != 0:
-        num_processes = min(args.num_processes, cpu_count())
+        num_processes = args.num_processes
         with Pool(processes=num_processes) as pool:
-            for _ in tqdm(pool.imap_unordered(process_line, lines), total=len(lines)):
-                pass
+            for _ in tqdm(
+                pool.imap_unordered(process_line, zip(lines, add_blank)),
+                total=len(lines),
+            ):
+                # 这里是缩进的代码块，表示循环体
+                pass  # 使用pass语句作为占位符
 
     print(f"bert生成完毕!, 共有{len(lines)}个bert.pt生成!")

clap_gen.py

@@ -27,7 +27,7 @@ def process_line(line):
             device = torch.device("cpu")
     wav_path, _, language_str, text, phones, tone, word2ph = line.strip().split("|")
 
-    clap_path = wav_path.replace(".WAV", ".wav").replace(".wav", ".emo.npy")
+    clap_path = wav_path.replace(".WAV", ".wav").replace(".wav", ".emo.pt")
     if os.path.isfile(clap_path):
         return