duixcom
【已解决，可参考】提交定制时显示Error: Error invoking remote method 'model/addModel': TypeError: SQLite3 can only bind numbers, strings, bigints, buffers, and null请问怎么解决
如图
运行日志如下
2025-03-11 20:00:44 heygem-tts | 2025-03-11 12:00:44.244 | INFO | tools.server.views_guiji:api_do_preprocess:96 - 收到训练请求：reference_audio='origin_audio/20250311200041089.wav' format='wav' lang='zh'
2025-03-11 20:00:44 heygem-tts | 2025-03-11 12:00:44.245 | INFO | tools.server.views_guiji:build_tts_item:46 - 创建会话目录：/code/sessions/20250311/480b3ab4439e4372bd4dd92faf8d12e1
2025-03-11 20:00:44 heygem-tts | 2025-03-11 12:00:44.246 | INFO | tools.server.views_guiji:build_tts_item:51 - reference_audio不是url地址，本地路径为：/code/data/origin_audio/20250311200041089.wav
2025-03-11 20:00:44 heygem-tts | 2025-03-11 12:00:44.248 | INFO | tools.server.views_guiji:api_do_preprocess:104 - 构建tts_item成功:{"session_id":"480b3ab4439e4372bd4dd92faf8d12e1","session_dir":"/code/sessions/20250311/480b3ab4439e4372bd4dd92faf8d12e1","raw_request":{"reference_audio":"/code/data/origin_audio/20250311200041089.wav","format":"wav","lang":"zh"},"raw_audio_path":"/code/data/origin_audio/20250311200041089.wav","reference_audios":[]}
2025-03-11 20:00:44 heygem-tts | 2025-03-11 12:00:44.248 | INFO | util.wav_util:clean_wav:139 - 开始清理音频：/code/data/origin_audio/20250311200041089.wav
2025-03-11 20:00:44 heygem-tts | 2025-03-11 12:00:44.249 | INFO | util.wav_util:format_wav:121 - 开始统一音频格式：/code/data/origin_audio/20250311200041089.wav
2025-03-11 20:00:44 heygem-tts | 2025-03-11 12:00:44.249 | INFO | util.wav_util:format_wav:125 - 音频统一转为16000 pcm s16，便于后面处理， 命令为：ffmpeg -i /code/data/origin_audio/20250311200041089.wav -ar 16000 -c:a pcm_s16le -y /code/data/origin_audio/format_20250311200041089.wav
2025-03-11 20:00:44 heygem-tts | ffmpeg version 4.4.2-0ubuntu0.22.04.1 Copyright (c) 2000-2021 the FFmpeg developers
2025-03-11 20:00:44 heygem-tts | built with gcc 11 (Ubuntu 11.2.0-19ubuntu1)
2025-03-11 20:00:44 heygem-tts | configuration: --prefix=/usr --extra-version=0ubuntu0.22.04.1 --toolchain=hardened --libdir=/usr/lib/x86_64-linux-gnu --incdir=/usr/include/x86_64-linux-gnu --arch=amd64 --enable-gpl --disable-stripping --enable-gnutls --enable-ladspa --enable-libaom --enable-libass --enable-libbluray --enable-libbs2b --enable-libcaca --enable-libcdio --enable-libcodec2 --enable-libdav1d --enable-libflite --enable-libfontconfig --enable-libfreetype --enable-libfribidi --enable-libgme --enable-libgsm --enable-libjack --enable-libmp3lame --enable-libmysofa --enable-libopenjpeg --enable-libopenmpt --enable-libopus --enable-libpulse --enable-librabbitmq --enable-librubberband --enable-libshine --enable-libsnappy --enable-libsoxr --enable-libspeex --enable-libsrt --enable-libssh --enable-libtheora --enable-libtwolame --enable-libvidstab --enable-libvorbis --enable-libvpx --enable-libwebp --enable-libx265 --enable-libxml2 --enable-libxvid --enable-libzimg --enable-libzmq --enable-libzvbi --enable-lv2 --enable-omx --enable-openal --enable-opencl --enable-opengl --enable-sdl2 --enable-pocketsphinx --enable-librsvg --enable-libmfx --enable-libdc1394 --enable-libdrm --enable-libiec61883 --enable-chromaprint --enable-frei0r --enable-libx264 --enable-shared
2025-03-11 20:00:44 heygem-tts | libavutil 56. 70.100 / 56. 70.100
2025-03-11 20:00:44 heygem-tts | libavcodec 58.134.100 / 58.134.100
2025-03-11 20:00:44 heygem-tts | libavformat 58. 76.100 / 58. 76.100
2025-03-11 20:00:44 heygem-tts | libavdevice 58. 13.100 / 58. 13.100
2025-03-11 20:00:44 heygem-tts | libavfilter 7.110.100 / 7.110.100
2025-03-11 20:00:44 heygem-tts | libswscale 5. 9.100 / 5. 9.100
2025-03-11 20:00:44 heygem-tts | libswresample 3. 9.100 / 3. 9.100
2025-03-11 20:00:44 heygem-tts | libpostproc 55. 9.100 / 55. 9.100
2025-03-11 20:00:44 heygem-tts | Guessed Channel Layout for Input Stream #0.0 : stereo
2025-03-11 20:00:44 heygem-tts | Input #0, wav, from '/code/data/origin_audio/20250311200041089.wav':
2025-03-11 20:00:44 heygem-tts | Metadata:
2025-03-11 20:00:44 heygem-tts | encoder : Lavf58.76.100
2025-03-11 20:00:44 heygem-tts | Duration: 00:01:44.44, bitrate: 1411 kb/s
2025-03-11 20:00:44 heygem-tts | Stream #0:0: Audio: pcm_s16le ([1][0][0][0] / 0x0001), 44100 Hz, stereo, s16, 1411 kb/s
2025-03-11 20:00:44 heygem-tts | Stream mapping:
2025-03-11 20:00:44 heygem-tts | Stream #0:0 -> #0:0 (pcm_s16le (native) -> pcm_s16le (native))
2025-03-11 20:00:44 heygem-tts | Press [q] to stop, [?] for help
2025-03-11 20:00:44 heygem-tts | Output #0, wav, to '/code/data/origin_audio/format_20250311200041089.wav':
2025-03-11 20:00:44 heygem-tts | Metadata:
2025-03-11 20:00:44 heygem-tts | ISFT : Lavf58.76.100
2025-03-11 20:00:44 heygem-tts | Stream #0:0: Audio: pcm_s16le ([1][0][0][0] / 0x0001), 16000 Hz, stereo, s16, 512 kb/s
2025-03-11 20:00:44 heygem-tts | Metadata:
2025-03-11 20:00:44 heygem-tts | encoder : Lavc58.134.100 pcm_s16le
2025-03-11 20:00:44 heygem-tts | size= 1kB time=00:00:00.00 bitrate=N/A speed=N/A
size= 6528kB time=00:01:44.44 bitrate= 512.0kbits/s speed= 754x
2025-03-11 20:00:44 heygem-tts | video:0kB audio:6528kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 0.001167%
2025-03-11 20:00:44 heygem-tts | 2025-03-11 12:00:44.499 | INFO | util.wav_util:format_wav:128 - wav标准格式化成功，/code/data/origin_audio/20250311200041089.wav -> /code/data/origin_audio/format_20250311200041089.wav
2025-03-11 20:00:44 heygem-tts | 2025-03-11 12:00:44.501 | INFO | util.wav_util:remove_noise:18 - 开始给wav去噪, raw_path:/code/data/origin_audio/format_20250311200041089.wav, output:/code/data/origin_audio/denoise_20250311200041089.wav
2025-03-11 20:00:46 heygem-tts | Audio Noise Reduction
2025-03-11 20:00:46 heygem-tts | time interval: 2283.554271 ms
2025-03-11 20:00:46 heygem-tts | 2025-03-11 12:00:46.959 | INFO | util.wav_util:format_wav:121 - 开始统一音频格式：/code/data/origin_audio/denoise_20250311200041089.wav
2025-03-11 20:00:46 heygem-tts | 2025-03-11 12:00:46.960 | INFO | util.wav_util:format_wav:125 - 音频统一转为16000 pcm s16，便于后面处理， 命令为：ffmpeg -i /code/data/origin_audio/denoise_20250311200041089.wav -ar 16000 -c:a pcm_s16le -y /code/data/origin_audio/format_denoise_20250311200041089.wav
2025-03-11 20:00:46 heygem-tts | ffmpeg version 4.4.2-0ubuntu0.22.04.1 Copyright (c) 2000-2021 the FFmpeg developers
2025-03-11 20:00:46 heygem-tts | built with gcc 11 (Ubuntu 11.2.0-19ubuntu1)
2025-03-11 20:00:46 heygem-tts | configuration: --prefix=/usr --extra-version=0ubuntu0.22.04.1 --toolchain=hardened --libdir=/usr/lib/x86_64-linux-gnu --incdir=/usr/include/x86_64-linux-gnu --arch=amd64 --enable-gpl --disable-stripping --enable-gnutls --enable-ladspa --enable-libaom --enable-libass --enable-libbluray --enable-libbs2b --enable-libcaca --enable-libcdio --enable-libcodec2 --enable-libdav1d --enable-libflite --enable-libfontconfig --enable-libfreetype --enable-libfribidi --enable-libgme --enable-libgsm --enable-libjack --enable-libmp3lame --enable-libmysofa --enable-libopenjpeg --enable-libopenmpt --enable-libopus --enable-libpulse --enable-librabbitmq --enable-librubberband --enable-libshine --enable-libsnappy --enable-libsoxr --enable-libspeex --enable-libsrt --enable-libssh --enable-libtheora --enable-libtwolame --enable-libvidstab --enable-libvorbis --enable-libvpx --enable-libwebp --enable-libx265 --enable-libxml2 --enable-libxvid --enable-libzimg --enable-libzmq --enable-libzvbi --enable-lv2 --enable-omx --enable-openal --enable-opencl --enable-opengl --enable-sdl2 --enable-pocketsphinx --enable-librsvg --enable-libmfx --enable-libdc1394 --enable-libdrm --enable-libiec61883 --enable-chromaprint --enable-frei0r --enable-libx264 --enable-shared
2025-03-11 20:00:46 heygem-tts | libavutil 56. 70.100 / 56. 70.100
2025-03-11 20:00:46 heygem-tts | libavcodec 58.134.100 / 58.134.100
2025-03-11 20:00:46 heygem-tts | libavformat 58. 76.100 / 58. 76.100
2025-03-11 20:00:46 heygem-tts | libavdevice 58. 13.100 / 58. 13.100
2025-03-11 20:00:46 heygem-tts | libavfilter 7.110.100 / 7.110.100
2025-03-11 20:00:46 heygem-tts | libswscale 5. 9.100 / 5. 9.100
2025-03-11 20:00:46 heygem-tts | libswresample 3. 9.100 / 3. 9.100
2025-03-11 20:00:46 heygem-tts | libpostproc 55. 9.100 / 55. 9.100
2025-03-11 20:00:46 heygem-tts | Guessed Channel Layout for Input Stream #0.0 : stereo
2025-03-11 20:00:46 heygem-tts | Input #0, wav, from '/code/data/origin_audio/denoise_20250311200041089.wav':
2025-03-11 20:00:46 heygem-tts | Duration: 00:01:44.44, bitrate: 1024 kb/s
2025-03-11 20:00:46 heygem-tts | Stream #0:0: Audio: pcm_f32le ([3][0][0][0] / 0x0003), 16000 Hz, stereo, flt, 1024 kb/s
2025-03-11 20:00:46 heygem-tts | Stream mapping:
2025-03-11 20:00:46 heygem-tts | Stream #0:0 -> #0:0 (pcm_f32le (native) -> pcm_s16le (native))
2025-03-11 20:00:46 heygem-tts | Press [q] to stop, [?] for help
2025-03-11 20:00:46 heygem-tts | Output #0, wav, to '/code/data/origin_audio/format_denoise_20250311200041089.wav':
2025-03-11 20:00:46 heygem-tts | Metadata:
2025-03-11 20:00:46 heygem-tts | ISFT : Lavf58.76.100
2025-03-11 20:00:46 heygem-tts | Stream #0:0: Audio: pcm_s16le ([1][0][0][0] / 0x0001), 16000 Hz, stereo, s16, 512 kb/s
2025-03-11 20:00:46 heygem-tts | Metadata:
2025-03-11 20:00:46 heygem-tts | encoder : Lavc58.134.100 pcm_s16le
2025-03-11 20:00:47 heygem-tts | size= 2kB time=00:00:00.00 bitrate=N/A speed=N/A
size= 6528kB time=00:01:44.41 bitrate= 512.1kbits/s speed=1.15e+03x
2025-03-11 20:00:47 heygem-tts | video:0kB audio:6528kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 0.001167%
2025-03-11 20:00:47 heygem-tts | 2025-03-11 12:00:47.086 | INFO | util.wav_util:format_wav:128 - wav标准格式化成功，/code/data/origin_audio/denoise_20250311200041089.wav -> /code/data/origin_audio/format_denoise_20250311200041089.wav
2025-03-11 20:00:47 heygem-tts | 2025-03-11 12:00:47.088 | INFO | util.wav_util:clean_wav:156 - 音频清理完成，新文件路径：/code/data/origin_audio/denoise_20250311200041089.wav
2025-03-11 20:00:47 heygem-tts | 2025-03-11 12:00:47.104 | INFO | util.wav_util:split_audio:98 - 开始分割文件，原文件:/code/data/origin_audio/format_denoise_20250311200041089.wav, 输出目录：/code/sessions/20250311/480b3ab4439e4372bd4dd92faf8d12e1
2025-03-11 20:00:48 heygem-tts | 2025-03-11 12:00:48.411 | INFO | util.wav_util:_process_audio:86 - 根据静音分割失败，尝试从原始音频中截取20s返回, 文件:/code/data/origin_audio/format_denoise_20250311200041089.wav
2025-03-11 20:00:48 heygem-tts | 2025-03-11 12:00:48.414 | INFO | util.wav_util:split_audio:113 - 文件分割结束，结果为：['/code/sessions/20250311/480b3ab4439e4372bd4dd92faf8d12e1/format_denoise_20250311200041089_part0.wav']
2025-03-11 20:00:48 heygem-tts | 2025-03-11 12:00:48.414 | INFO | asr_fun:asr:102 - fun asr start, wav_path:/code/sessions/20250311/480b3ab4439e4372bd4dd92faf8d12e1/format_denoise_20250311200041089_part0.wav
2025-03-11 20:00:48 heygem-tts | 2025-03-11 12:00:48.418 | INFO | asr_fun:init_conn:40 - connect to url
2025-03-11 20:00:48 heygem-tts | 2025-03-11 12:00:48.419 | WARNING | asr_fun:init_conn:53 - 建立funasr连接异常：[Errno 111] Connection refused
2025-03-11 20:00:48 heygem-tts | Traceback (most recent call last):
2025-03-11 20:00:48 heygem-tts | File "/code/asr_fun.py", line 41, in init_conn
2025-03-11 20:00:48 heygem-tts | self.websocket = create_connection(uri, ssl=ssl_context, sslopt=ssl_opt)
2025-03-11 20:00:48 heygem-tts | File "/opt/conda/envs/python310/lib/python3.10/site-packages/websocket/_core.py", line 646, in create_connection
2025-03-11 20:00:48 heygem-tts | websock.connect(url, **options)
2025-03-11 20:00:48 heygem-tts | File "/opt/conda/envs/python310/lib/python3.10/site-packages/websocket/_core.py", line 256, in connect
2025-03-11 20:00:48 heygem-tts | self.sock, addrs = connect(
2025-03-11 20:00:48 heygem-tts | File "/opt/conda/envs/python310/lib/python3.10/site-packages/websocket/_http.py", line 145, in connect
2025-03-11 20:00:48 heygem-tts | sock = _open_socket(addrinfo_list, options.sockopt, options.timeout)
2025-03-11 20:00:48 heygem-tts | File "/opt/conda/envs/python310/lib/python3.10/site-packages/websocket/_http.py", line 232, in _open_socket
2025-03-11 20:00:48 heygem-tts | raise err
2025-03-11 20:00:48 heygem-tts | File "/opt/conda/envs/python310/lib/python3.10/site-packages/websocket/_http.py", line 209, in _open_socket
2025-03-11 20:00:48 heygem-tts | sock.connect(address)
2025-03-11 20:00:48 heygem-tts | ConnectionRefusedError: [Errno 111] Connection refused
2025-03-11 20:01:24 heygem-tts | 2025-03-11 12:01:24.538 | ERROR | tools.server.views_guiji:api_do_preprocess:118 - An error occurred: 'NoneType' object has no attribute 'send'
2025-03-11 20:01:24 heygem-tts | Stack trace:
2025-03-11 20:01:24 heygem-tts | Traceback (most recent call last):
2025-03-11 20:01:24 heygem-tts | File "/code/tools/server/views_guiji.py", line 105, in api_do_preprocess
2025-03-11 20:01:24 heygem-tts | rt = generate_reference_info(tts_item)
2025-03-11 20:01:24 heygem-tts | File "/code/tools/server/views_guiji.py", line 76, in generate_reference_info
2025-03-11 20:01:24 heygem-tts | text = asr_fun.asr(a_file)
2025-03-11 20:01:24 heygem-tts | File "/code/asr_fun.py", line 120, in asr
2025-03-11 20:01:24 heygem-tts | result: dict = rcg.close(timeout=3)
2025-03-11 20:01:24 heygem-tts | File "/code/asr_fun.py", line 86, in close
2025-03-11 20:01:24 heygem-tts | self.websocket.send(message)
2025-03-11 20:01:24 heygem-tts | AttributeError: 'NoneType' object has no attribute 'send'
2025-03-11 20:01:24 heygem-tts |
2025-03-11 20:01:24 heygem-tts | 2025-03-11 12:01:24.538 | INFO | tools.server.views_guiji:api_do_preprocess:121 - 训练返回结果：{'code': -1, 'msg': "'NoneType' object has no attribute 'send'"}
2025-03-11 20:01:24 heygem-tts | INFO: 172.18.0.1:51416 - "POST /v1/preprocess_and_tran HTTP/1.1" 200 OK
main.log
] 2025-03-11 20:11:13 [info] audio split done 2025-03-11 20:11:13 [debug] ~ preprocessAndTran ~ param: {"format":"wav","reference_audio":"origin_audio/20250311201110474.wav","lang":"zh"} 2025-03-11 20:11:54 [debug] ~ train ~ res: { code: -1, msg: "'NoneType' object has no attribute 'send'" } 2025-03-11 20:11:54 [debug] [SQL Run]: INSERT INTO f2f_model (name, video_path, audio_path, voice_id, created_at) VALUES (?, ?, ?, ?, ?) [ '测试', '20250311201110474.MOV', 'origin_audio\\20250311201110474.wav', false, 1741695114242 ]
Looking at the log, it seems that the heygem - asr service cannot be connected. Please confirm whether the heygem - asr has been successfully launched. If it has, please also paste the key logs.
我这边的asr日志是这样的
heygem-asr | [W shape_analysis.cpp:841] failed PropagateTensorShapeOnNode with schema: heygem-asr | aten::pad(Tensor self, int[] pad, str mode="constant", float? value=None) -> (Tensor) heygem-asr | %input.827 : Float(*, *, , requires_grad=0, device=cuda:0) = aten::pad(%input.825, %4848, %4849, %4850), scope: __module.model.encoders/__module.model.encoders.40/__module.model.encoders.40.self_attn/__module.model.encoders.40.self_attn.pad_fn # /usr/local/lib/python3.8/dist-packages/torch/nn/modules/padding.py:23:0 heygem-asr | heygem-asr | [W shape_analysis.cpp:841] failed PropagateTensorShapeOnNode with schema: heygem-asr | aten::pad(Tensor self, int[] pad, str mode="constant", float? value=None) -> (Tensor) heygem-asr | %input.847 : Float(, *, , requires_grad=0, device=cuda:0) = aten::pad(%input.845, %4962, %4963, %4964), scope: __module.model.encoders/__module.model.encoders.41/__module.model.encoders.41.self_attn/__module.model.encoders.41.self_attn.pad_fn # /usr/local/lib/python3.8/dist-packages/torch/nn/modules/padding.py:23:0 heygem-asr | heygem-asr | [W shape_analysis.cpp:841] failed PropagateTensorShapeOnNode with schema: heygem-asr | aten::pad(Tensor self, int[] pad, str mode="constant", float? value=None) -> (Tensor) heygem-asr | %input.867 : Float(, *, , requires_grad=0, device=cuda:0) = aten::pad(%input.865, %5076, %5077, %5078), scope: __module.model.encoders/__module.model.encoders.42/__module.model.encoders.42.self_attn/__module.model.encoders.42.self_attn.pad_fn # /usr/local/lib/python3.8/dist-packages/torch/nn/modules/padding.py:23:0 heygem-asr | heygem-asr | [W shape_analysis.cpp:841] failed PropagateTensorShapeOnNode with schema: heygem-asr | aten::pad(Tensor self, int[] pad, str mode="constant", float? value=None) -> (Tensor) heygem-asr | %input.887 : Float(, *, , requires_grad=0, device=cuda:0) = aten::pad(%input.885, %5190, %5191, %5192), scope: __module.model.encoders/__module.model.encoders.43/__module.model.encoders.43.self_attn/__module.model.encoders.43.self_attn.pad_fn # /usr/local/lib/python3.8/dist-packages/torch/nn/modules/padding.py:23:0 heygem-asr | heygem-asr | [W shape_analysis.cpp:841] failed PropagateTensorShapeOnNode with schema: heygem-asr | aten::pad(Tensor self, int[] pad, str mode="constant", float? value=None) -> (Tensor) heygem-asr | %input.907 : Float(, *, , requires_grad=0, device=cuda:0) = aten::pad(%input.905, %5304, %5305, %5306), scope: __module.model.encoders/__module.model.encoders.44/__module.model.encoders.44.self_attn/__module.model.encoders.44.self_attn.pad_fn # /usr/local/lib/python3.8/dist-packages/torch/nn/modules/padding.py:23:0 heygem-asr | heygem-asr | [W shape_analysis.cpp:841] failed PropagateTensorShapeOnNode with schema: heygem-asr | aten::pad(Tensor self, int[] pad, str mode="constant", float? value=None) -> (Tensor) heygem-asr | %input.927 : Float(, *, , requires_grad=0, device=cuda:0) = aten::pad(%input.925, %5418, %5419, %5420), scope: __module.model.encoders/__module.model.encoders.45/__module.model.encoders.45.self_attn/__module.model.encoders.45.self_attn.pad_fn # /usr/local/lib/python3.8/dist-packages/torch/nn/modules/padding.py:23:0 heygem-asr | heygem-asr | [W shape_analysis.cpp:841] failed PropagateTensorShapeOnNode with schema: heygem-asr | aten::pad(Tensor self, int[] pad, str mode="constant", float? value=None) -> (Tensor) heygem-asr | %input.947 : Float(, *, , requires_grad=0, device=cuda:0) = aten::pad(%input.945, %5532, %5533, %5534), scope: __module.model.encoders/__module.model.encoders.46/__module.model.encoders.46.self_attn/__module.model.encoders.46.self_attn.pad_fn # /usr/local/lib/python3.8/dist-packages/torch/nn/modules/padding.py:23:0 heygem-asr | heygem-asr | [W shape_analysis.cpp:841] failed PropagateTensorShapeOnNode with schema: heygem-asr | aten::pad(Tensor self, int[] pad, str mode="constant", float? value=None) -> (Tensor) heygem-asr | %input.967 : Float(, *, , requires_grad=0, device=cuda:0) = aten::pad(%input.965, %5646, %5647, %5648), scope: __module.model.encoders/__module.model.encoders.47/__module.model.encoders.47.self_attn/__module.model.encoders.47.self_attn.pad_fn # /usr/local/lib/python3.8/dist-packages/torch/nn/modules/padding.py:23:0 heygem-asr | heygem-asr | [W shape_analysis.cpp:841] failed PropagateTensorShapeOnNode with schema: heygem-asr | aten::pad(Tensor self, int[] pad, str mode="constant", float? value=None) -> (Tensor) heygem-asr | %input.987 : Float(, *, *, requires_grad=0, device=cuda:0) = aten::pad(%input.985, %5760, %5761, %5762), scope: __module.model.encoders/__module.model.encoders.48/__module.model.encoders.48.self_attn/__module.model.encoders.48.self_attn.pad_fn # /usr/local/lib/python3.8/dist-packages/torch/nn/modules/padding.py:23:0
- Ensure that there is sufficient memory (32G).
- Ensure that the resource - saving mode of Docker is not enabled.
- Wait for about 5 minutes after starting or restarting, as heygem - asr needs to download the model files.
- 确保内存足够（32G）
- 确保没有开启Docker的省资源模式
- 启动或重启后等待5分钟左右，heygem-asr需要下载模型文件
内存必须32G以上，我就是在16G内存不行的情况下加了一根内存条就解决了
同时这其中有个小插曲，内存条加上后docker里面还是显示只有16G，依旧会存在不能正常运行的情况，这个时候需要编辑一个配置文件，如下所示
.wslconfig 使用 .wslconfig 为 WSL 上运行的所有已安装的发行版配置全局设置。
默认情况下，.wslconfig 文件不存在。 它必须创建并存储在%UserProfile%目录中才能应用这些配置设置。 用于在作为 WSL 2 版本运行的所有已安装的 Linux 发行版中全局配置设置。 只能用于 WSL 2 运行的发行版。 作为 WSL 1 运行的发行版不受此配置的影响，因为它们不作为虚拟机运行。 要访问 %UserProfile% 目录，请在 PowerShell 中使用 cd ~ 访问主目录（通常是用户配置文件 C:\Users<UserName>），或者可以打开 Windows 文件资源管理器并在地址栏中输入 %UserProfile%。 该目录路径应类似于：C:\Users<UserName>.wslconfig。
在此目录下创建记事本文件，命名为 .wslconfig ，内容为（以我的内存为32G为例）： [wsl2] memory=32GB
保存好后cmd里面输入wsl --shutdown 然后重启docker即可