ZcChat icon indicating copy to clipboard operation
ZcChat copied to clipboard
verified publisher icon Zao-chen

语言输出和对话问题

Open Ice-peer opened this issue 4 months ago • 8 comments

确认在求助前尝试过以下办法（在[]内输入x确认）

  • [x] 我确认我使用的是最新的ZcChat
  • [ ] 我已经认真阅读过README、WIKI以及教程视频

**你遇到的问题*打开vits网页点播放器生成显示’无法获取音频数据，请查看日志‘；对话框只显示中文情感，但是打开历史记录会有中文情感和中日双语回答(用的OPENAI,因为letta一直在Connecting) 对问题的清晰简洁的描述。例如，我不知道如何打开对话框。

描述你尝试过的方法 对您尝试过的任何的清晰简洁的描述。例如，双击立绘。

附加上下文还有我下载ZCchat的文件夹里面没有README啊，我也不知道WIKI网址 在此处添加的任何其他上下文或屏幕截图。

Ice-peer avatar Sep 06 '25 10:09 Ice-peer

提供一下log文件

Zao-chen avatar Sep 10 '25 06:09 Zao-chen

D:\新建文件夹\py310\lib\site-packages\pydantic_internal_fields.py:127: UserWarning: Field "model_type" has conflict with protected namespace "model_".

You may be able to resolve this warning by setting model_config['protected_namespaces'] = (). warnings.warn( Building prefix dict from the default dictionary ... 2025-09-10 22:55:56 [DEBUG] Building prefix dict from the default dictionary ... [in init.initialize:113] Loading model from cache C:\Users\icdpe\AppData\Local\Temp\jieba.cache 2025-09-10 22:55:56 [DEBUG] Loading model from cache C:\Users\icdpe\AppData\Local\Temp\jieba.cache [in init.initialize:132] Loading model cost 1.697 seconds. 2025-09-10 22:55:58 [DEBUG] Loading model cost 1.697 seconds. [in init.initialize:164] Prefix dict has been built successfully. 2025-09-10 22:55:58 [DEBUG] Prefix dict has been built successfully. [in init.initialize:166] 2025-09-10 22:56:17 [INFO] initializing identifier [in langid.load_model:162] 2025-09-10 22:56:47 [INFO] model_type:VITS model_id:0 n_speakers:7 vits_path:D:\新建文件夹\data\models\YuzuSoft_Vits\365_epochs.pth [in ModelManager._load_model_from_path:331] 2025-09-10 22:56:47 [INFO] PyTorch Version: 2.2.1+cpu Cuda available:False Device type:cpu [in ModelManager.log_device_info:170] 2025-09-10 22:56:49 [INFO] Using CPU on 13th Gen Intel(R) Core(TM) i9-13900HX with 24 cores and 32 threads. Total memory: 32GB [in ModelManager.log_device_info:187] 2025-09-10 22:56:49 [INFO] [VITS] 7 speakers [in ModelManager.model_init:106] 2025-09-10 22:56:49 [INFO] 7 speakers in total. [in ModelManager.model_init:115] 2025-09-10 22:56:49 [INFO] Loading large_pinyin [in phrases_dict.phrases_dict_init:7] 2025-09-10 22:56:51 [DEBUG] Looking up time zone info from registry [in win32._get_localzone_name:58] 2025-09-10 22:56:51 [INFO] Scheduler started [in base.start:214] 2025-09-10 22:56:51 [INFO] Added job "clean_task" to job store "default" [in base._real_add_job:1090] 2025-09-10 22:56:51 [INFO] Not using ngrok. [in app.:88]

  • Serving Flask app 'app'
  • Debug mode: off 2025-09-10 22:56:51 [INFO] WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead.
  • Running on all addresses (0.0.0.0)
  • Running on http://127.0.0.1:23456
  • Running on http://192.168.10.5:23456 [in _internal._log:187] 2025-09-10 22:56:51 [INFO] Press CTRL+C to quit [in _internal._log:187] 2025-09-10 22:58:14 [INFO] 127.0.0.1 - - [10/Sep/2025 22:58:14] "GET / HTTP/1.1" 200 - [in _internal._log:187] 2025-09-10 22:58:15 [INFO] 127.0.0.1 - - [10/Sep/2025 22:58:15] "GET /static/css/plugins/bootstrap.min.css HTTP/1.1" 200 - [in _internal._log:187] 2025-09-10 22:58:15 [INFO] 127.0.0.1 - - [10/Sep/2025 22:58:15] "GET /static/js/plugins/jquery-3.7.1.min.js HTTP/1.1" 200 - [in _internal._log:187] 2025-09-10 22:58:15 [INFO] 127.0.0.1 - - [10/Sep/2025 22:58:15] "GET /static/js/plugins/bootstrap.bundle.min.js HTTP/1.1" 200 - [in _internal._log:187] 2025-09-10 22:58:15 [INFO] 127.0.0.1 - - [10/Sep/2025 22:58:15] "GET /static/css/fileinput.min.css HTTP/1.1" 200 - [in _internal._log:187] 2025-09-10 22:58:15 [INFO] 127.0.0.1 - - [10/Sep/2025 22:58:15] "GET /static/css/plugins/select2-bootstrap-5-theme.min.css HTTP/1.1" 200 - [in _internal._log:187] 2025-09-10 22:58:15 [INFO] 127.0.0.1 - - [10/Sep/2025 22:58:15] "GET /static/js/index.js HTTP/1.1" 200 - [in _internal._log:187] 2025-09-10 22:58:15 [INFO] 127.0.0.1 - - [10/Sep/2025 22:58:15] "GET /static/js/plugins/fileinput.min.js HTTP/1.1" 200 - [in _internal._log:187] 2025-09-10 22:58:15 [INFO] 127.0.0.1 - - [10/Sep/2025 22:58:15] "GET /static/js/plugins/select2.min.js HTTP/1.1" 200 - [in _internal._log:187] 2025-09-10 22:58:15 [INFO] 127.0.0.1 - - [10/Sep/2025 22:58:15] "GET /static/css/style.css HTTP/1.1" 200 - [in _internal._log:187] 2025-09-10 22:58:15 [INFO] 127.0.0.1 - - [10/Sep/2025 22:58:15] "GET /static/css/pages/index.css HTTP/1.1" 200 - [in _internal._log:187] 2025-09-10 22:58:15 [INFO] 127.0.0.1 - - [10/Sep/2025 22:58:15] "GET /static/css/plugins/select2.min.css HTTP/1.1" 200 - [in _internal._log:187] 2025-09-10 22:58:15 [INFO] 127.0.0.1 - - [10/Sep/2025 22:58:15] "GET /voice/speakers HTTP/1.1" 200 - [in _internal._log:187] 2025-09-10 22:58:15 [INFO] 127.0.0.1 - - [10/Sep/2025 22:58:15] "POST /voice/default_parameter HTTP/1.1" 200 - [in _internal._log:187] 2025-09-10 22:58:15 [INFO] 127.0.0.1 - - [10/Sep/2025 22:58:15] "GET /favicon.ico HTTP/1.1" 404 - [in internal.log:187] 2025-09-10 22:58:29 [INFO] [VITS] id:0 format:wav lang:auto length:1.0 noise:0.33 noisew:0.4 segment_size:50 [in views.voice_vits_api:148] 2025-09-10 22:58:29 [INFO] [VITS] len:8 text：你好,こんにちは [in views.voice_vits_api:150] 2025-09-10 22:58:29 [DEBUG] [JA]你好,こんにちは[JA] [in sentence.sentence_split_and_markup:181] ERROR: Mecab_load() in mecab.cpp: Cannot open D:\鏂板缓鏂囦欢澶筡py310\lib\site-packages\pyopenjtalk\open_jtalk_dic_utf_8-1.11. 2025-09-10 22:58:30 [ERROR] Exception on /voice/vits [POST] [in app.log_exception:1744] Traceback (most recent call last): File "D:\新建文件夹\py310\lib\site-packages\flask\app.py", line 2528, in wsgi_app response = self.full_dispatch_request() File "D:\新建文件夹\py310\lib\site-packages\flask\app.py", line 1825, in full_dispatch_request rv = self.handle_user_exception(e) File "D:\新建文件夹\py310\lib\site-packages\flask_cors\extension.py", line 194, in wrapped_function return cors_after_request(app.make_response(f(*args, **kwargs))) File "D:\新建文件夹\py310\lib\site-packages\flask\app.py", line 1823, in full_dispatch_request rv = self.dispatch_request() File "D:\新建文件夹\py310\lib\site-packages\flask\app.py", line 1799, in dispatch_request return self.ensure_sync(self.view_functions[rule.endpoint])(**view_args) File "D:\新建文件夹\tts_app\voice_api\auth.py", line 10, in check_api_key return func(*args, **kwargs) File "D:\新建文件夹\tts_app\voice_api\views.py", line 200, in voice_vits_api audio = tts_manager.vits_infer(state) File "D:\新建文件夹\manager\TTSManager.py", line 296, in vits_infer sentence_audio = model.infer(sentence, state["id"], state["noise"], state["noisew"], state["length"]) File "D:\新建文件夹\vits\vits.py", line 68, in infer stn_tst = self.get_cleaned_text(text, self.hps_ms, cleaned=cleaned) File "D:\新建文件夹\vits\vits.py", line 57, in get_cleaned_text text_norm = text_to_sequence(text, hps.symbols, hps.data.text_cleaners) File "D:\新建文件夹\vits\text_init.py", line 21, in text_to_sequence cleaned_text = clean_text(text, cleaner_names) File "D:\新建文件夹\vits\text_init.py", line 31, in clean_text text = cleaner(text) File "D:\新建文件夹\vits\text\cleaners.py", line 76, in japanese_cleaners text = re.sub(r'[JA](.?)[JA]', lambda x: clean(x.group(1)) + ' ', text) File "D:\新建文件夹\py310\lib\re.py", line 209, in sub return _compile(pattern, flags).sub(repl, string, count) File "D:\新建文件夹\vits\text\cleaners.py", line 76, in text = re.sub(r'[JA](.?)[JA]', lambda x: clean(x.group(1)) + ' ', text) File "D:\新建文件夹\vits\text\cleaners.py", line 72, in clean text = japanese_to_romaji_with_accent(text) File "D:\新建文件夹\vits\text\japanese.py", line 100, in japanese_to_romaji_with_accent labels = pyopenjtalk.extract_fullcontext(sentence) File "D:\新建文件夹\py310\lib\site-packages\pyopenjtalk_init.py", line 147, in extract_fullcontext njd_features = run_frontend(text) File "D:\新建文件夹\py310\lib\site-packages\pyopenjtalk_init.py", line 209, in run_frontend _global_jtalk = OpenJTalk(dn_mecab=OPEN_JTALK_DICT_DIR) File "pyopenjtalk\openjtalk.pyx", line 142, in pyopenjtalk.openjtalk.OpenJTalk.cinit RuntimeError: Failed to initalize Mecab 2025-09-10 22:58:30 [INFO] 127.0.0.1 - - [10/Sep/2025 22:58:30] "POST /voice/vits HTTP/1.1" 500 - [in internal.log:187] 2025-09-10 22:59:04 [INFO] [VITS] id:0 format:wav lang:auto length:1.0 noise:0.33 noisew:0.4 segment_size:50 [in views.voice_vits_api:148] 2025-09-10 22:59:04 [INFO] [VITS] len:8 text：你好,こんにちは [in views.voice_vits_api:150] 2025-09-10 22:59:04 [DEBUG] [JA]你好,こんにちは[JA] [in sentence.sentence_split_and_markup:181] ERROR: Mecab_load() in mecab.cpp: Cannot open D:\鏂板缓鏂囦欢澶筡py310\lib\site-packages\pyopenjtalk\open_jtalk_dic_utf_8-1.11. 2025-09-10 22:59:04 [ERROR] Exception on /voice/vits [POST] [in app.log_exception:1744] Traceback (most recent call last): File "D:\新建文件夹\py310\lib\site-packages\flask\app.py", line 2528, in wsgi_app response = self.full_dispatch_request() File "D:\新建文件夹\py310\lib\site-packages\flask\app.py", line 1825, in full_dispatch_request rv = self.handle_user_exception(e) File "D:\新建文件夹\py310\lib\site-packages\flask_cors\extension.py", line 194, in wrapped_function return cors_after_request(app.make_response(f(*args, **kwargs))) File "D:\新建文件夹\py310\lib\site-packages\flask\app.py", line 1823, in full_dispatch_request rv = self.dispatch_request() File "D:\新建文件夹\py310\lib\site-packages\flask\app.py", line 1799, in dispatch_request return self.ensure_sync(self.view_functions[rule.endpoint])(**view_args) File "D:\新建文件夹\tts_app\voice_api\auth.py", line 10, in check_api_key return func(*args, **kwargs) File "D:\新建文件夹\tts_app\voice_api\views.py", line 200, in voice_vits_api audio = tts_manager.vits_infer(state) File "D:\新建文件夹\manager\TTSManager.py", line 296, in vits_infer sentence_audio = model.infer(sentence, state["id"], state["noise"], state["noisew"], state["length"]) File "D:\新建文件夹\vits\vits.py", line 68, in infer stn_tst = self.get_cleaned_text(text, self.hps_ms, cleaned=cleaned) File "D:\新建文件夹\vits\vits.py", line 57, in get_cleaned_text text_norm = text_to_sequence(text, hps.symbols, hps.data.text_cleaners) File "D:\新建文件夹\vits\text_init.py", line 21, in text_to_sequence cleaned_text = clean_text(text, cleaner_names) File "D:\新建文件夹\vits\text_init.py", line 31, in clean_text text = cleaner(text) File "D:\新建文件夹\vits\text\cleaners.py", line 76, in japanese_cleaners text = re.sub(r'[JA](.?)[JA]', lambda x: clean(x.group(1)) + ' ', text) File "D:\新建文件夹\py310\lib\re.py", line 209, in sub return _compile(pattern, flags).sub(repl, string, count) File "D:\新建文件夹\vits\text\cleaners.py", line 76, in text = re.sub(r'[JA](.?)[JA]', lambda x: clean(x.group(1)) + ' ', text) File "D:\新建文件夹\vits\text\cleaners.py", line 72, in clean text = japanese_to_romaji_with_accent(text) File "D:\新建文件夹\vits\text\japanese.py", line 100, in japanese_to_romaji_with_accent labels = pyopenjtalk.extract_fullcontext(sentence) File "D:\新建文件夹\py310\lib\site-packages\pyopenjtalk_init.py", line 147, in extract_fullcontext njd_features = run_frontend(text) File "D:\新建文件夹\py310\lib\site-packages\pyopenjtalk_init.py", line 209, in run_frontend _global_jtalk = OpenJTalk(dn_mecab=OPEN_JTALK_DICT_DIR) File "pyopenjtalk\openjtalk.pyx", line 142, in pyopenjtalk.openjtalk.OpenJTalk.cinit RuntimeError: Failed to initalize Mecab 2025-09-10 22:59:04 [INFO] 127.0.0.1 - - [10/Sep/2025 22:59:04] "POST /voice/vits HTTP/1.1" 500 - [in internal.log:187] 2025-09-10 23:00:06 [INFO] [VITS] id:0 format:wav lang:auto length:1.0 noise:0.33 noisew:0.4 segment_size:50 [in views.voice_vits_api:148] 2025-09-10 23:00:06 [INFO] [VITS] len:8 text：你好,こんにちは [in views.voice_vits_api:150] 2025-09-10 23:00:06 [DEBUG] [JA]你好,こんにちは[JA] [in sentence.sentence_split_and_markup:181] ERROR: Mecab_load() in mecab.cpp: Cannot open D:\鏂板缓鏂囦欢澶筡py310\lib\site-packages\pyopenjtalk\open_jtalk_dic_utf_8-1.11. 2025-09-10 23:00:06 [ERROR] Exception on /voice/vits [POST] [in app.log_exception:1744] Traceback (most recent call last): File "D:\新建文件夹\py310\lib\site-packages\flask\app.py", line 2528, in wsgi_app response = self.full_dispatch_request() File "D:\新建文件夹\py310\lib\site-packages\flask\app.py", line 1825, in full_dispatch_request rv = self.handle_user_exception(e) File "D:\新建文件夹\py310\lib\site-packages\flask_cors\extension.py", line 194, in wrapped_function return cors_after_request(app.make_response(f(*args, **kwargs))) File "D:\新建文件夹\py310\lib\site-packages\flask\app.py", line 1823, in full_dispatch_request rv = self.dispatch_request() File "D:\新建文件夹\py310\lib\site-packages\flask\app.py", line 1799, in dispatch_request return self.ensure_sync(self.view_functions[rule.endpoint])(**view_args) File "D:\新建文件夹\tts_app\voice_api\auth.py", line 10, in check_api_key return func(*args, **kwargs) File "D:\新建文件夹\tts_app\voice_api\views.py", line 200, in voice_vits_api audio = tts_manager.vits_infer(state) File "D:\新建文件夹\manager\TTSManager.py", line 296, in vits_infer sentence_audio = model.infer(sentence, state["id"], state["noise"], state["noisew"], state["length"]) File "D:\新建文件夹\vits\vits.py", line 68, in infer stn_tst = self.get_cleaned_text(text, self.hps_ms, cleaned=cleaned) File "D:\新建文件夹\vits\vits.py", line 57, in get_cleaned_text text_norm = text_to_sequence(text, hps.symbols, hps.data.text_cleaners) File "D:\新建文件夹\vits\text_init.py", line 21, in text_to_sequence cleaned_text = clean_text(text, cleaner_names) File "D:\新建文件夹\vits\text_init.py", line 31, in clean_text text = cleaner(text) File "D:\新建文件夹\vits\text\cleaners.py", line 76, in japanese_cleaners text = re.sub(r'[JA](.?)[JA]', lambda x: clean(x.group(1)) + ' ', text) File "D:\新建文件夹\py310\lib\re.py", line 209, in sub return _compile(pattern, flags).sub(repl, string, count) File "D:\新建文件夹\vits\text\cleaners.py", line 76, in text = re.sub(r'[JA](.?)[JA]', lambda x: clean(x.group(1)) + ' ', text) File "D:\新建文件夹\vits\text\cleaners.py", line 72, in clean text = japanese_to_romaji_with_accent(text) File "D:\新建文件夹\vits\text\japanese.py", line 100, in japanese_to_romaji_with_accent labels = pyopenjtalk.extract_fullcontext(sentence) File "D:\新建文件夹\py310\lib\site-packages\pyopenjtalk_init.py", line 147, in extract_fullcontext njd_features = run_frontend(text) File "D:\新建文件夹\py310\lib\site-packages\pyopenjtalk_init.py", line 209, in run_frontend _global_jtalk = OpenJTalk(dn_mecab=OPEN_JTALK_DICT_DIR) File "pyopenjtalk\openjtalk.pyx", line 142, in pyopenjtalk.openjtalk.OpenJTalk.cinit RuntimeError: Failed to initalize Mecab 2025-09-10 23:00:06 [INFO] 127.0.0.1 - - [10/Sep/2025 23:00:06] "POST /voice/vits HTTP/1.1" 500 - [in _internal._log:187]

Ice-peer avatar Sep 10 '25 15:09 Ice-peer

对话框右键立绘打开，报错的原因是你vits使用了中文路径

Zao-chen avatar Sep 11 '25 23:09 Zao-chen

对话框右键立绘打开，报错的原因是你vits使用了中文路径

哦哦，网站可以了，但是又报错了。2025-09-12 16:30:10 [Error] 解析 JSON 错误： [json.exception.parse_error.101] parse error at line 1, column 1: attempting to parse an empty input; check that your input string or stream contains the expected JSON

Ice-peer avatar Sep 12 '25 08:09 Ice-peer

提供一下日志

Zao-chen avatar Sep 16 '25 06:09 Zao-chen

提供一下日志

log.txt

Ice-peer avatar Sep 16 '25 07:09 Ice-peer

2025-09-16 15:26:57 [Info] [tachie] 获取到 API 响应： "" 2025-09-16 15:26:57 [Critical] [tachie] 解析 JSON 错误： [json.exception.parse_error.101] parse error at line 1, column 1: attempting to parse an empty input; check that your input string or stream contains the expected JSON 2025-09-16 15:27:04 [Info] [UnknownWindow] 读取到message "正常|[error] opeanai请求错误 |错误error" opanai已经请求错误了，你的llm配置可能有问题

Zao-chen avatar Sep 16 '25 12:09 Zao-chen

2025-09-16 15:26:57 [Info] [tachie] 获取到 API 响应： "" 2025-09-16 15:26:57 [Critical] [tachie] 解析 JSON 错误： [json.exception.parse_error.101] parse error at line 1, column 1: attempting to parse an empty input; check that your input string or stream contains the expected JSON 2025-09-16 15:27:04 [Info] [UnknownWindow] 读取到message "正常|[error] opeanai请求错误 |错误error" opanai已经请求错误了，你的llm配置可能有问题 是OPEN AI 的问题吗，但是之前没开语音就没有这个问题啊，不是vits 的问题吗。开始没开语音的日志是正常的吗

Ice-peer avatar Sep 16 '25 13:09 Ice-peer