vra / talkgpt4all Goto Github PK
View Code? Open in Web Editor NEWA voice chatbot based on GPT4All and talkGPT, running on your local pc!
License: MIT License
A voice chatbot based on GPT4All and talkGPT, running on your local pc!
License: MIT License
执行 talkgpt4all 出错
Traceback (most recent call last):
File "D:\ProgramData\Anaconda3\envs\talkgpt4all\lib\runpy.py", line 196, in _run_module_as_main
return run_code(code, main_globals, None,
File "D:\ProgramData\Anaconda3\envs\talkgpt4all\lib\runpy.py", line 86, in run_code
exec(code, run_globals)
File "D:\ProgramData\Anaconda3\envs\talkgpt4all\Scripts\talkgpt4all.exe_main.py", line 7, in
File "D:\ProgramData\Anaconda3\envs\talkgpt4all\lib\site-packages\talkgpt4all_init.py", line 40, in main
chat_bot = GPT4AllChatBot(
File "D:\ProgramData\Anaconda3\envs\talkgpt4all\lib\site-packages\talkgpt4all\chat.py", line 25, in init
self.gpt_model = GPT4All(gpt_model_name, allow_download=True)
File "D:\ProgramData\Anaconda3\envs\talkgpt4all\lib\site-packages\gpt4all\gpt4all.py", line 97, in init
self.config: ConfigType = self.retrieve_model(model_name, model_path=model_path, allow_download=allow_download, verbose=verbose)
File "D:\ProgramData\Anaconda3\envs\talkgpt4all\lib\site-packages\gpt4all\gpt4all.py", line 187, in retrieve_model
config["path"] = GPT4All.download_model(model_filename, model_path, verbose=verbose, url=url)
File "D:\ProgramData\Anaconda3\envs\talkgpt4all\lib\site-packages\gpt4all\gpt4all.py", line 234, in download_model
response = make_request()
File "D:\ProgramData\Anaconda3\envs\talkgpt4all\lib\site-packages\gpt4all\gpt4all.py", line 229, in make_request
raise ValueError(f'Request failed: HTTP {response.status_code} {response.reason}')
ValueError: Request failed: HTTP 404 Not Found
加上梯子也不行,也未显示是哪个URL 404了
谢谢
Hi, after re install of everything, there's still these errors about Cannot specify extra characters after a string enclosed in quotation marks, Text splitted to sentences and strange characters? Then the missing .wav file playsound error. I wonder if you found anything more about it?
TEXT SPLIT AND STRANGE CHARACTERS
Listening...
==> answer: I am an AI language model and do not have the ability to feel emotions or experience physical sensations. However, I am here to assist you with any qu
estions or tasks you may have. How can I help you today?
Text splitted to sentences.
['I am an AI language model and do not have the ability to feel emotions or experience physical sensations.', 'However, I am here to assist you with any questions
or tasks you may have.', 'How can I help you today?']
aɪ æm ən aɪ læŋɡwɪd͡ʒ mɑdəl ænd du nɑt hæv ðə əbɪləti tə fil ɪmoʊʃənz ɔɹ ɪkspɪɹiəns fɪzɪkəl sɛnseɪʃənz. << STRANGE CHARACTERS
[!] Character '͡' not found in the vocabulary. Discarding it.
Processing time: 1.6647748947143555
Real-time factor: 0.10804181312824211
Windows PowerShell
Copyright (C) Microsoft Corporation. All rights reserved.
PS C:\talkGPT4All-main> & c:/talkGPT4All-main/.venv/Scripts/Activate.ps1
(.venv) PS C:\talkGPT4All-main> & c:/talkGPT4All-main/.venv/Scripts/python.exe c:/talkGPT4All-main/src/talkgpt4all/chat.py
==> GPT4All model: mistral-7b-instruct-v0.1.Q4_0.gguf, Whisper model: base
tts_models/en/ljspeech/glow-tts is already downloaded.
vocoder_models/en/ljspeech/multiband-melgan is already downloaded.
Using model: glow_tts
Setting up Audio Processor...
| > sample_rate:22050
| > resample:False
| > num_mels:80
| > log_func:np.log10
| > min_level_db:-100
| > frame_shift_ms:None
| > frame_length_ms:None
| > ref_level_db:0
| > fft_size:1024
| > power:1.1
| > preemphasis:0.0
| > griffin_lim_iters:60
| > signal_norm:False
| > symmetric_norm:True
| > mel_fmin:50.0
| > mel_fmax:7600.0
| > pitch_fmin:1.0
| > pitch_fmax:640.0
| > spec_gain:1.0
| > stft_pad_mode:reflect
| > max_norm:1.0
| > clip_norm:True
| > do_trim_silence:True
| > trim_db:60
| > do_sound_norm:False
| > do_amp_to_db_linear:True
| > do_amp_to_db_mel:True
| > do_rms_norm:False
| > db_level:None
| > stats_path:None
| > base:10
| > hop_length:256
| > win_length:1024
Vocoder Model: multiband_melgan
Setting up Audio Processor...
| > sample_rate:22050
| > resample:False
| > num_mels:80
| > log_func:np.log10
| > min_level_db:-100
| > frame_shift_ms:None
| > frame_length_ms:None
| > ref_level_db:0
| > fft_size:1024
| > power:1.5
| > preemphasis:0.0
| > griffin_lim_iters:60
| > signal_norm:True
| > symmetric_norm:True
| > mel_fmin:50.0
| > mel_fmax:7600.0
| > pitch_fmin:0.0
| > pitch_fmax:640.0
| > spec_gain:1.0
| > stft_pad_mode:reflect
| > max_norm:4.0
| > clip_norm:True
| > do_trim_silence:True
| > trim_db:60
| > do_sound_norm:False
| > do_amp_to_db_linear:True
| > do_amp_to_db_mel:True
| > do_rms_norm:False
| > db_level:None
| > stats_path:C:\Users\S373NTH\AppData\Local\tts\vocoder_models--en--ljspeech--multiband-melgan\scale_stats.npy
| > base:10
| > hop_length:256
| > win_length:1024
Generator Model: multiband_melgan_generator
Discriminator Model: melgan_multiscale_discriminator
Listening...
==> answer: I am an AI language model and do not have the ability to feel emotions or experience physical sensations. However, I am here to assist you with any qu
estions or tasks you may have. How can I help you today?
Text splitted to sentences.
['I am an AI language model and do not have the ability to feel emotions or experience physical sensations.', 'However, I am here to assist you with any questions
or tasks you may have.', 'How can I help you today?']
aɪ æm ən aɪ læŋɡwɪd͡ʒ mɑdəl ænd du nɑt hæv ðə əbɪləti tə fil ɪmoʊʃənz ɔɹ ɪkspɪɹiəns fɪzɪkəl sɛnseɪʃənz.
[!] Character '͡' not found in the vocabulary. Discarding it.
Processing time: 1.6647748947143555
Real-time factor: 0.10804181312824211
Error 305 for command:
open "C:\Users\S373NTH\AppData\Local\Temp\talkgpt4all-73qu1lv2.wav"
Cannot specify extra characters after a string enclosed in quotation marks.
Error 305 for command:
close "C:\Users\S373NTH\AppData\Local\Temp\talkgpt4all-73qu1lv2.wav"
Cannot specify extra characters after a string enclosed in quotation marks.
Failed to close the file: "C:\Users\S373NTH\AppData\Local\Temp\talkgpt4all-73qu1lv2.wav"
Traceback (most recent call last):
File "c:\talkGPT4All-main\src\talkgpt4all\chat.py", line 126, in
chat_bot.run()
File "c:\talkGPT4All-main\src\talkgpt4all\chat.py", line 38, in run
self._text_to_voice(answer)
File "c:\talkGPT4All-main\src\talkgpt4all\chat.py", line 74, in _text_to_voice
playsound(tmp_file.name)
File "C:\talkGPT4All-main.venv\Lib\site-packages\playsound.py", line 72, in _playsoundWin
winCommand(u'open {}'.format(sound))
File "C:\talkGPT4All-main.venv\Lib\site-packages\playsound.py", line 64, in winCommand
raise PlaysoundException(exceptionMessage)
playsound.PlaysoundException:
Error 305 for command:
open "C:\Users\S373NTH\AppData\Local\Temp\talkgpt4all-73qu1lv2.wav"
Cannot specify extra characters after a string enclosed in quotation marks.
(.venv) PS C:\talkGPT4All-main>
Tested it with recent ggml-gpt4all-j-v1.3-groovy model.
The workaround is to modify the call to gpt_model.chat_completion(...). Passing arguments default_prompt_footer=True and default_prompt_header=True has fixed it.
我想卸载它,怎么才能完全删除安装过程中下载的文件呢?
运行环境:Mac M1 Pro
which python3
/Users/xxx/project/talkGPT4All/talkgpt4all/bin/python3
运行命令:
python3 chat.py --platform mac-m1
[1] 76330 segmentation fault /Users/xxx/project/talkGPT4All/talkgpt4all/bin/python3 chat.py mac-m1
然后就弹出Python崩了,发送错误报告给Apple
另外,这个项目的依赖中似乎缺了一个:pyttsx3,不安装会报错
ModuleNotFoundError: No module named 'pyttsx3'
已经星标,很棒的项目。Yunfeng Wang 👍
现在gpt4all 已经可以一键下载安装,普惠了普通人,talkgtp4all建议考虑这一点,如何高效的结合并运用起来
I'm getting the following error "AttributeError: 'GPT4All' object has no attribute 'chat_completion'" and not sure what to do? After searching all I can come up with is article about removed attribute? I might be using wrong version of python? Maybe 'chat_completion doesn't work anymore?
Also the the "'nopython' keyword argument was not supplied to the 'numba.jit' decorator. The implicit default value for this argument is currently False, but it will be changed to True in Numba 0.59.0" Error but I think I can ignore this?
PS C:\TalkGPTforAll> python - version
Python 3.10.0 (tags/v3.10.0:b494f59, Oct 4 2021, 19:00:18) [MSC v.1929 64 bit (AMD64)] on win32
Win10/64
AMD RY5
GTX1060GPU 3GB
PS C:\TalkGPTforAll> talkgpt4all
Found model file at C:\\Users\\S373NTH\\.cache\\gpt4all\ggml-gpt4all-j-v1.3-groovy.bin
gptj_model_load: loading model from 'C:\\Users\\S373NTH\\.cache\\gpt4all\ggml-gpt4all-j-v1.3-groovy.bin' - please wait ...
gptj_model_load: n_vocab = 50400
gptj_model_load: n_ctx = 2048
gptj_model_load: n_embd = 4096
gptj_model_load: n_head = 16
gptj_model_load: n_layer = 28
gptj_model_load: n_rot = 64
gptj_model_load: f16 = 2
gptj_model_load: ggml ctx size = 5401.45 MB
gptj_model_load: kv self size = 896.00 MB
gptj_model_load: ................................... done
gptj_model_load: model size = 3609.38 MB / num tensors = 285
Listening...
C:\Users\S373NTH\AppData\Local\Programs\Python\Python310\lib\site-packages\whisper\timing.py:58: NumbaDeprecationWarning: The 'nopython' keyword argument wa
s not supplied to the 'numba.jit' decorator. The implicit default value for this argument is currently False, but it will be changed to True in Numba 0.59.0
. See https://numba.readthedocs.io/en/stable/reference/deprecation.html#deprecation-of-object-mode-fall-back-behaviour-when-using-jit for details.
def backtrace(trace: np.ndarray):
===> question: Have a good night. Have a good night.ipes Hello. I hope you lack any time your story.
Traceback (most recent call last):
File "C:\Users\S373NTH\AppData\Local\Programs\Python\Python310\lib\runpy.py", line 196, in _run_module_as_main
return run_code(code, main_globals, None,
File "C:\Users\S373NTH\AppData\Local\Programs\Python\Python310\lib\runpy.py", line 86, in run_code
exec(code, run_globals)
File "C:\Users\S373NTH\AppData\Local\Programs\Python\Python310\Scripts\talkgpt4all.exe_main.py", line 7, in
File "C:\Users\S373NTH\AppData\Local\Programs\Python\Python310\lib\site-packages\talkgpt4all_init.py", line 44, in main
chat_bot.run()
File "C:\Users\S373NTH\AppData\Local\Programs\Python\Python310\lib\site-packages\talkgpt4all\chat.py", line 27, in run
answer = self.run_gpt(input_words)
File "C:\Users\S373NTH\AppData\Local\Programs\Python\Python310\lib\site-packages\talkgpt4all\chat.py", line 46, in run_gpt
response = self.gpt_model.chat_completion(
AttributeError: 'GPT4All' object has no attribute 'chat_completion'
PS C:\TalkGPTforAll>
PS C:\TalkGPTforAll> pip list
Package Version Editable project location
aiohttp 3.8.4
aiosignal 1.3.1
altgraph 0.17.3
annotated-types 0.5.0
anyio 3.7.0
async-generator 1.10
async-timeout 4.0.2
attrs 23.1.0
beautifulsoup4 4.12.2
BingImageCreator 0.4.2
blinker 1.6.2
boto3 1.26.114
botocore 1.29.154
certifi 2023.5.7
cffi 1.15.1
charset-normalizer 3.1.0
click 8.1.3
colorama 0.4.6
comtypes 1.2.0
dataclasses-json 0.5.14
DateTime 5.1
EasyProcess 1.1
EdgeGPT 0.3.2
einops 0.6.1
elevenlabslib 0.5.2
encodec 0.1.1
entrypoint2 1.1
exceptiongroup 1.1.1
ffmpeg 1.4
ffmpeg-python 0.2.0
filelock 3.12.2
Flask 2.3.2
frozenlist 1.3.3
fsspec 2023.6.0
funcy 2.0
future 0.18.3
gitdb 4.0.10
GitPython 3.1.31
glob2 0.7
gpt4all 1.0.5
greenlet 2.0.2
h11 0.14.0
httpcore 0.17.2
httpx 0.24.1
huggingface-hub 0.16.2
idna 3.4
itsdangerous 2.1.2
Jinja2 3.1.2
jmespath 1.0.1
kokoroio 0.0.3
langchain 0.0.270
langsmith 0.0.25
llvmlite 0.40.1rc1
markdown-it-py 3.0.0
MarkupSafe 2.1.3
marshmallow 3.20.1
mdurl 0.1.2
more-itertools 9.1.0
MouseInfo 0.1.3
mpmath 1.3.0
mss 9.0.1
multidict 6.0.4
mypy-extensions 1.0.0
networkx 3.1
notification 0.2.1
numba 0.57.0
numexpr 2.8.5
numpy 1.24.3
openai 0.27.4
openai-whisper 20230314
outcome 1.2.0
packaging 23.1
pefile 2023.2.7
Pillow 9.5.0
pip 23.3.1
playsound 1.3.0
plyer 2.1.0
prompt-toolkit 3.0.38
PyAudio 0.2.13
PyAutoGUI 0.9.54
pycparser 2.21
pydantic 2.2.1
pydantic_core 2.6.1
pydub 0.25.1
pygame 2.4.0
PyGetWindow 0.0.9
Pygments 2.15.1
pyinstaller 5.10.1
pyinstaller-hooks-contrib 2023.3
pyjokes 0.6.0
pyllamacpp 2.4.1
PyMsgBox 1.0.9
pypandoc 1.11
pyperclip 1.8.2
pypiwin32 223
PyRect 0.2.0
pyscreenshot 3.1
PyScreeze 0.1.29
PySocks 1.7.1
python-dateutil 2.8.2
pyttsx3 2.90
pytweening 1.0.7
pytz 2023.3
pywhatkit 5.4
pywin32 306
pywin32-ctypes 0.2.1
PyYAML 6.0
random2 1.0.1
regex 2023.6.3
requests 2.31.0
rich 13.4.2
s3transfer 0.6.1
safetensors 0.3.1
scipy 1.11.1
selenium 4.10.0
setuptools 57.4.0
six 1.16.0
smmap 5.0.0
sniffio 1.3.0
socksio 1.0.0
sortedcontainers 2.4.0
sounddevice 0.4.6
soundfile 0.12.1
soupsieve 2.4.1
SpeechRecognition 3.10.0
speedtest 0.0.1
SQLAlchemy 2.0.20
sseclient-py 1.7.2
suno-bark 0.0.1a0 C:\Users\S373NTH\modules\bark
sympy 1.12
talkgpt4all 2.1.1
tenacity 8.2.3
tiktoken 0.3.1
tokenizers 0.13.3
torch 2.0.1
torchaudio 2.0.2
torchvision 0.15.2
tqdm 4.65.0
transformers 4.30.2
trio 0.22.0
trio-websocket 0.10.3
typing 3.7.4.3
typing_extensions 4.6.3
typing-inspect 0.9.0
urllib3 1.26.16
vocos 0.0.3
wcwidth 0.2.6
websockets 11.0.3
Werkzeug 2.3.6
wheel 0.41.1
whisper 1.1.10
wikipedia 1.4.0
wsproto 1.2.0
yarl 1.9.2
zope.interface 6.0
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.