sociallyineptweeb / languageleapai

Your Personal Multilingual AI Translator

LanguageLeapAI

LEAP across Language barriers by using AI to converse with other online users from across the globe! LanguageLeapAI aims to provide you a real-time language AI assistant that can understand and speak your desired language fluently. (Targeted towards English to Japanese and German as of right now)

Setup Guide: https://www.youtube.com/watch?v=bN5UaEkIPGM

Showcase: https://www.youtube.com/watch?v=UY7sRB60wZ4

Integration of AI Entities

This project integrates 3 free and open-source AI systems:

1. WhisperAI: General-purpose Speech Recognition Model developed by OpenAI that can perform multilingual speech recognition.
2. DeepL Translator: Powered by neural networks and the latest AI innovations for natural-sounding translations
3. Voicevox: Japanese Deep-Learning AI Voice Synthesizer

WhisperAI and Voicevox both have docker images available on DockerHub, so we will be building and running them both via a Docker Compose file. DeepL can be interacted with by signing up for a free plan and interacting with its REST API up to 500,000 character limit / month. If DeepL is unavailable in your country, an option to use Google Translate instead is available.

How it works

LanguageLeapAI is made up of 2 main python programs.

Voice Translator

The first, voice_translator.py, records your microphone whenever a push-to-talk key is held down on the keyboard. Once this key is released, it saves your voice in an audio file which is then sent to WhisperAI's transcribe endpoint which runs Automatic Speech Recognition (ASR) on it. After a response containing your speech as text is received, this text is then translated using DeepL's REST API.

The translated text is then sent to Voicevox which performs text-to-speech and generates an audio file voiced in Japanese. This file is then played to your target application's microphone input and your speakers/headphones.

Since Voicevox only takes in Japanese text as input and generates speech in Japanese, the project is technically only limited to Japanese as the target language. However, Voicevox can be replaced with any other text to speech program that can speak your desired language for limitless possibilities.

Thorsten has been added as a German TTS program.

Audio Subtitler

The second, subtitler.py, records your application's audio output and listens in the background for any speech. Once it has detected that a phrase/sentence is complete, it saves the audio into a wav file and sends it to WhisperAI's translate endpoint which translates the speech from the target language to English.

This English text is then displayed on screen using python's tkinter module, essentially acting as subtitles.

Applications

LanguageLeapAI's target audience is for users who want to chat with another but do not speak the same language. An example is an English-speaking user playing an online game in the Japan server but wants to use voice chat despite not knowing Japanese.

By running both subtitler.py and voice_translator.py, they can understand their fellow Japanese teammates by reading the english subtitles generated in real time. They can also speak English and the Japanese teammates will instead hear the translated Japanese speech generated by Voicevox.

However, this is not the only application of LanguageLeapAI.

Only using Audio Subtitler

User simply wants to understand what is being said with no need to speak. E.g. Watching a video / stream / movie in another language without subtitles. The user can choose to not run voice_translator.py and simply use subtitler.py.

Only using Voice Translator

User understands the language enough to listen and understand, but is afraid to speak the language for various reasons, e.g. Anonymity / Fear of messing up or offending. The user can choose to not run subtitler.py and simply use voice_translator.py.

Setup

Setting up LanguageLeapAI requires 3 crucial steps, so don't miss out on any of them!

1. Installing Services and Dependencies
2. Audio Routing
3. Writing your Environment file

Usage

To run LanguageLeapAI, you need to first run WhisperAI and Voicevox. They can either be run via Docker or using Google Colab.

Google Colab

If your GPU is not powerful enough, you may want to consider running WhisperAI and Voicevox using Google Colab's GPU.

Upload run_whisper_n_voicevox.ipynb file to Google drive, open the notebook with Google Colab and simply follow the instructions!

To run only whisper or voicevox on the cloud: Use either the run_whisper_colab.ipynb and run_voicevox_colab.ipynb Colab files instead!

Docker

Voicevox - JA

If you still want to run both Whisper and Voicevox on your computer, run these commands in the folder containing the docker-compose.yml file.

To run both WhisperAI and Voicevox:

docker-compose up -d

To stop running the containers:

docker-compose down

If you're running Windows Subsystem for Linux (WSL) don't forget to shut it down to reclaim your ram. This should only after you have stopped the containers and are done using the program.

wsl --shutdown

TTS Thorsten - DE

If you want to run a German version of Voicevox, you need to change the docker-compose file to the corresponding one. The TTS is the only thing that's changing, so make sure to also change the TARGET_LANGUAGE_CODE in your .env file.

To run both WhisperAI and Thorsten:

docker-compose -f docker-compose-de.yml up -d

To stop running the containers:

docker-compose down

Python Program

Run these commands in the src/ folder.

To run the Audio Subtitler:

python subtitler.py

To run the Voice Translator:

python voice_translator.py

To stop the python scripts, simply press Ctrl+C in the terminal.

Things to note

Some important things to keep in mind while using LanguageLeapAI.

Whisper's inconsistency

Do note that WhisperAI is not exactly the most accurate and will not transcribe speech correctly 100% of the time, so use at your own risk. Until OpenAI decides to improve the dataset that was used to train the Whisper models, this will have to do.

Also, Whisper is not designed to handle multiple concurrent requests at once. However, for subtitles to be updated in time, multiple requests are being sent asynchronously, so some requests might return an error.

Antivirus Web Protection

If you are running Whisper and Voicevox on the cloud using Google Colab, since we are using ngrok and localtunnel to host our services, the randomised public IP address that they provide might be blacklisted by your antivirus software. If the AI seems to stop working, it may be due to your antivirus blocking the connections to these public IP addresses. You may whitelist these IP addresses or just turn off your antivirus web protection at your own risk.

Voicevox voices

There are certain terms and conditions for using the voices from Voicevox, so do read up on these before using a specific speaker.

License

The code of LanguageLeapAI is released under the MIT License. See LICENSE for further details.

languageleapai's Issues

Wave_write object has not attributte '_file'

Im testing the Google Colab method but now im getting this error:

FYI: Is working properly the endpoints created in colab.

Very strange bug

Finally, the subtitler works, but can't hear anything from my PC.

But when I use the voice translator, it worked 1 time, it translated my voice but after,
Any running application start to crash, until windows crashes itself and becomes blank.
And when windows don't crash, I can't stop the docker, and docker desktop won't stop running.

I called a friend for help and he couldn't help me, It's the weirdest thing that happend to me, and I have no idea how to fix that.
It happen everytime I launch the voice translator.

Request timeout for subtitler.py

I tested on short and long voices where the latter just returns to request timeout

Edit: Actually it's not about the duration, it now occurs often somehow both short and long.

Voicevox problem: Can't play voice

[SOLVED] See below
I can't use them both, Google want to subscribe to Colab Pro

How can I use them both at the same time ?
Or it's not necessary ?

do i failed at some point ??

This openai WHISPER model has some serious problem

(ldo) G:\PRINT G0\LanguageLeapAI-main\LanguageLeapAI-main\src>python subtitler.py
Request timeout
Request timeout
Request timeout
Request timeout

not working at all

(ldo) G:\PRINT G0\LanguageLeapAI-main\LanguageLeapAI-main\src>python voice_translator.py
English: copy.
Japanese: をコピーします。
when i just said something complete not copy.

(ldo) G:\PRINT G0\LanguageLeapAI-main\LanguageLeapAI-main\src>python voice_translator.py
English: Thank you.
Japanese: ありがとうございます。
when i just say hey and it return thank you

(ldo) G:\PRINT G0\LanguageLeapAI-main\LanguageLeapAI-main\src>python voice_translator.py
English: Are you?
Japanese: あなたはそうですか？
how are you return are you

and voice vox part just dont work at all ,colab tells me if i dont use voicevox clooud gpu just shut it down

ModuleNotFoundError

➜ ~ python3.8 subtitltler.py
Traceback (most recent call last):
File "subtitltler.py", line 11, in
from modules.audio_translate import translate_audio
ModuleNotFoundError: No module named 'modules.audio_translate'; 'modules' is not a package

How do I get voice IDs?

I have a question, if I want to change the voice to a male voice, how do I get the voice IDs to obtain the voice I want for the value VOICE_ID in the .env?

Unable to reach Whisper, ensure that it is running, or the WHISPER_BASE_URL variable is set correctly

both urls are the same

Error while executing subtitler.py

Not sure about this error

VoiceVox voice ID

where did you get those?

WinError 10061

how i can fix this

Docker only works with a NVIDIA GPU

amd gpu support?

I got the following error while trying to startup the docker container:

Error response from daemon: failed to create shim task: OCI runtime create failed: runc create failed: unable to start container process: error during container init: error running hook #0: error running hook: exit status 1, stdout: , stderr: Auto-detected mode as 'legacy' nvidia-container-cli: initialization error: WSL environment detected but no adapters were found: unknown

On another PC, this issue was solved by installing the Nvidia GPU driver, but I have an amd GPU on my main machine💀. Is there any way to change the requirements of the docker to get AMD GPUs to work?

Type Error

Umm, I already installed the requirements.txt and also fill the .env file already done in google colab but I'm still getting an error

TypeError on line 10 of src\modules\asr.py

About the Google Colab

even this is free, it also has a capacity in which it reaches the limit you no longer use the GPU, and you'll just have to use another account :D

Trying to ONLY run the subtitler

nothing shows up when trying to run python subtitler.py.

whisper is running as well.

have a problem with getenv()

problem: line 9, in BASE_URL = getenv('WHISPER_BASE_URL')

TypeError: 'str' object is not collable

Code:

1)from os import getenv
2)from pathlib import Path
3)
4)import requests
5)from dotenv import load_dotenv
6)
7)load_dotenv()
8)
9)BASE_URL = getenv('WHISPER_BASE_URL')

OSError: [Errno -9985] Device unavailable

So DeepL isn't avaible in my country so I tried https://pypi.org/project/googletrans/ which is really simple but give out bad translation (good enough for me) and you only need to change 4 lines but when I run the voice_translator.py I get this error

This is my .env on the audio devices id part

This is my get_audio_output_ids output

JSONDecodeError when running voice_translator.py

I assumed it was an error with my audio ids but I checked all of them. I am running this on google colab and all of that is working fine.

Running voicevox.py also spawns this error

Google colab

Okay now is working the "server" created at google colab, but is returning me a 500 request error:

Do you think there is an error when im not using the colab GPU?

got an error when using subtitler.py

It worked fine before, I don't know what's going on.

whisper return {"detail":"Not Found"}

As written in the title, the response of the request to '{BASE_URL}/asr?task=transcribe&language=en&output=json' in transcribe() is {"detail":"Not Found"}, is there a solution?

Additionally, when the transcribe() function ends, the program terminates. Is it possible to prevent it?

I don't even know why this is

argument out of range voice_translator.py / request timeout subtitler.py

Ive followed the instructions in the audio and env files, also installed everything said in the readme file but when i try to launch the codes i get argument out of range for voice_translator.py and the request timeout for subtitler.py. i tried playing with the values in the env file but without any change. any help?

DeepL alternatives?

I can't sign up for a free account due to being in an unsupported country so I was wondering if there are other alternatives?

Google Trans Issue

[Feature] Showing transcribed and translated text to the screen

Why?

Games like Valorant only allow push to talk, that mean I have to set 1 keybind (v) for Speech To Text, and 1 keybind (n) to actually talk in the game.

Everytime I actually say something, I want to know if the transcribed and translated text are correct before I actually send the voice to other players. So if showing them to the screen like how Subtitler doing. If would be easier to use.

I'm not familiar with Python so I couldn't get it to work.

I'm looking forward to your ideas and desicions.

Thanks

I get some errors (i probably did something wrong)

How do i fix these errors? Do i have some incompatible version of python or something?

can't to get a response from voicevox in colab

I managed to get the project to work. However I can't seem to get a response from voicevox in colab

the additional print statements are added like this:

I tired adding the port number to the URL and got a connection refused error

I ended up hosting voicevox on me local machine and it works.

Is this due to the Antivirus Web Protection you mentioned?
If so how do I should I configure my firewall? I tried to allow inbound connections like this but the error stays the same:

DeepL Alternatives

got any guide for this :D

Request Timeout

i see too much Request Timeout how i fix this and translate too wrong

voice_translator.py stopping without error after attempting to send API calls to Whisper/DeepL/VoiceVox

Issue

I have been experimenting for hours without luck. Whenever I run voice_translator.py, it seems to stop the script after attempting to request data. It doesn't output anything as well. Very randomly, it decides to work, but 99% of the time I am unable to get it to work.

I ran Whisper and VoiceVox through Docker before, but thinking that somehow that was an issue despite having the resources, I'm hosting them currently on Colab. I've attempted using different Python versions from 3.8 to 3.11.

I've documented all my testing below. I hope this helps pinpoint something. Maybe I'm overlooking something very apparent or maybe it's a specific issue on my environment, though I'm just running on Windows 10.

Testings with voice_translator.py

I've had the best results via Docker. Where it's able to at least transcribe. But even that is unfortunately inconsistent. I've logged the contents of the variables in voice_translator.py where it shows it doesn't pass after DeepL.

I even went as far as omitting certain steps:

Skipping transcription
No result from DeepL, script stops without throwing error.

Skipping translation
Here it seems to get responses from both audio_query and synthesis calls, but stops before playing the audio. Also no error thrown.

Testings with module scripts

However, it succeeds the calls running the scripts manually. Same result with either Docker or Colab.
voicevox.py (I even tried translating here)

asr.py

Extra info

For some reason, I'm not able to see the logs in Docker. But when I switched to Colab, it's logging bad requests whenever the transcribe fails when running voice_translator.py. The 200 responses were from the times I manually ran asr.py.

Unable to reach whisper

I'm getting a problem while running the voice_translator it says

even though the variables are correct ig.

Voice sounds incredibly robotic

Hello,

I was just curious on if you had a potential fix for preventing this from sounding incredibly robotic. I had resorted to tweaking the settings below but for whatever reason it clips at points (despite having a good mic although I don't think this is the reason) and just sounds off compared to your initial video.

VOICE_ID=20

# Type: float
SPEED_SCALE=1.0
VOLUME_SCALE=3.0
INTONATION_SCALE=1.5
PRE_PHONEME_LENGTH=1.0
POST_PHONEME_LENGTH=1.0

Problems with Voicevox

Soooooooo here i am opening an Issue because i've spent about two hours trying to fix it by myself and i'm tired of it now. Hopefully somebody can help.

I initially ran everything in google Collab and was constantly getting time-outs from my voicevox collab instance. I tested the translation in the asr.py file ans DeepL and whisper a playing niceley and that works just fine.
I get a translation of what i said printed in the terminal, and then the the problems start.
My Voicevox doesn't print anything to the collab console and won't react in the test in voicevox.py nor when i try to actually use it in the voice_translator.py.

The next thing i did is try to run just Voicevox it locally because maybe collab was playing up. I quickly noticed that i doesn't work with amd gpus so i pulled the cpu image from docker hub and ran it manually

1. docker pull voicevox/voicevox_engine:cpu-ubuntu20.04-latest
2. docker run --rm -it -p '127.0.0.1:50021:50021' voicevox/voicevox_engine:cpu-ubuntu20.04-latest

And now some things were happening (i was getting outputs from voicevox, yay!) but other still weren't.
Now everytime i say something i get following erros from the Console in which Voicevox is running:

INFO:     Started server process [1]
INFO:     Waiting for application startup.
reading /tmp/tmp5wmph5yu ... 57
emitting double-array: 100% |###########################################|

done!
INFO:     Application startup complete.
INFO:     Uvicorn running on http://0.0.0.0:50021 (Press CTRL+C to quit)
INFO:     172.17.0.1:48314 - "POST //audio_query?text=%E3%82%80%E3%81%8B%E3%81%97%E3%81%82%E3%82%8B%E3%81%A8%E3%81%93%E3%82%8D%E3%81%AB%E3%80%81%E3%82%B8%E3%83%A3%E3%83%83%E3%82%AF%E3%81%A8%E3%81%84%E3%81%86%E7%94%B7%E3%81%AE%E5%AD%
90%E3%81%8C%E3%81%84%E3%81%BE%E3%81%97%E3%81%9F%E3%80%82%E3%82%B8%E3%83%A3%E3%83%83%E3%82%AF%E3%81%AF%E3%81%8A%E6%AF%8D%E3%81%95%E3%82%93%E3%81%A8%E4%B8%80%E7%B7%92%E3%81%AB%E4%BD%8F%E3%82%93%E3%81%A7%E3%81%84%E3%81%BE%E3%81%97%E3%8
1%9F%E3%80%82&speaker=15 HTTP/1.1" 404 Not Found
INFO:     172.17.0.1:48316 - "POST //synthesis?speaker=15 HTTP/1.1" 404 Not Found
^CINFO:     Shutting down
INFO:     Waiting for application shutdown.
INFO:     Application shutdown complete.
INFO:     Finished server process [1]

and these form the voicevox.py file:

Voicevox attempting to speak now...
Exception in thread Thread-1 (play_voice):
Exception in thread Traceback (most recent call last):
  File "C:\Python310\lib\threading.py", line 1009, in _bootstrap_inner
Thread-2 (play_voice):
Traceback (most recent call last):
  File "C:\Python310\lib\threading.py", line 1009, in _bootstrap_inner
    self.run()
  File "C:\Python310\lib\threading.py", line 946, in run
    self.run()
  File "C:\Python310\lib\threading.py", line 946, in run
    self._target(*self._args, **self._kwargs)
  File "C:\*\LanguageLeapAI-main\src\modules\voicevox.py", line 29, in play_voice
    self._target(*self._args, **self._kwargs)
  File "C:\*\LanguageLeapAI-main\src\modules\voicevox.py", line 29, in play_voice
    data, fs = sf.read(VOICEVOX_WAV_PATH, dtype='float32')
  File "C:\*\LanguageLeapAI-main\lib\site-packages\soundfile.py", line 285, in read
    data, fs = sf.read(VOICEVOX_WAV_PATH, dtype='float32')
  File "C:\*\LanguageLeapAI-main\lib\site-packages\soundfile.py", line 285, in read
    with SoundFile(file, 'r', samplerate, channels,
  File "C:\*\LanguageLeapAI-main\lib\site-packages\soundfile.py", line 658, in __init__
    with SoundFile(file, 'r', samplerate, channels,
  File "C:\*\LanguageLeapAI-main\lib\site-packages\soundfile.py", line 658, in __init__
    self._file = self._open(file, mode_int, closefd)
  File "C:\*\LanguageLeapAI-main\lib\site-packages\soundfile.py", line 1216, in _open
    self._file = self._open(file, mode_int, closefd)
  File "C:\*\LanguageLeapAI-main\lib\site-packages\soundfile.py", line 1216, in _open
    raise LibsndfileError(err, prefix="Error opening {0!r}: ".format(self.name))
soundfile.LibsndfileError: Error opening 'C:\\*\\LanguageLeapAI-main\\src\\audio\\voicevox.wav': Format not recognised.
    raise LibsndfileError(err, prefix="Error opening {0!r}: ".format(self.name))
soundfile.LibsndfileError: Error opening 'C:\\*\\LanguageLeapAI-main\\src\\audio\\voicevox.wav': Format not recognised.

Process finished with exit code 0

as well as these from the voice_translator.py: (as you can see, the translation part works)

English: This is a test sentence.
Japanese: これはテスト文です。
Exception in thread Exception in thread Thread-4 (play_voice):
Traceback (most recent call last):
  File "C:\Python310\lib\threading.py", line 1009, in _bootstrap_inner
Thread-3 (play_voice):
Traceback (most recent call last):
  File "C:\Python310\lib\threading.py", line 1009, in _bootstrap_inner
    self.run()    self.run()
  File "C:\Python310\lib\threading.py", line 946, in run

  File "C:\Python310\lib\threading.py", line 946, in run
    self._target(*self._args, **self._kwargs)
  File "C:\*\LanguageLeapAI-main\src\modules\voicevox.py", line 29, in play_voice
    self._target(*self._args, **self._kwargs)
  File "C:\*\LanguageLeapAI-main\src\modules\voicevox.py", line 29, in play_voice
    data, fs = sf.read(VOICEVOX_WAV_PATH, dtype='float32')
  File "C:\*\LanguageLeapAI-main\lib\site-packages\soundfile.py", line 285, in read
    data, fs = sf.read(VOICEVOX_WAV_PATH, dtype='float32')
  File "C:\*\LanguageLeapAI-main\lib\site-packages\soundfile.py", line 285, in read
    with SoundFile(file, 'r', samplerate, channels,
  File "C:\*\LanguageLeapAI-main\lib\site-packages\soundfile.py", line 658, in __init__
    with SoundFile(file, 'r', samplerate, channels,
  File "C:\*\LanguageLeapAI-main\lib\site-packages\soundfile.py", line 658, in __init__
    self._file = self._open(file, mode_int, closefd)
  File "C:\*\LanguageLeapAI-main\lib\site-packages\soundfile.py", line 1216, in _open
    self._file = self._open(file, mode_int, closefd)
  File "C:\*\LanguageLeapAI-main\lib\site-packages\soundfile.py", line 1216, in _open
    raise LibsndfileError(err, prefix="Error opening {0!r}: ".format(self.name))
soundfile.LibsndfileError: Error opening 'C:\\*\\LanguageLeapAI-main\\src\\audio\\voicevox.wav': Format not recognised.
    raise LibsndfileError(err, prefix="Error opening {0!r}: ".format(self.name))
soundfile.LibsndfileError: Error opening 'C:\\*\\LanguageLeapAI-main\\src\\audio\\voicevox.wav': Format not recognised.
Closing voice translator.

Process finished with exit code 0

So yeah, that's about what i've done so far.

Help would be most appreciated!

Couldn't find `CABLE Output (VB-Audio Virtual Cable)` in application settings.

According to Audio Routing setup guide, after setting up VoiceMeeter Banana, I have to set input device to CABLE Output (VB-Audio Virtual Cable) in the application settings. The problem is, I couldn't find it anywhere. All I found were VoiceMeeter Output (VB-Audio VoiceMeeter VAIO) and VoiceMeeter AUX Output (VB-Audio VoiceMeeter AUX VAIO)

Here is my VoiceMeeter Banana setup.

Thank you.

can't run the python programs

DeepL

i just want use subtitler do I still need to use DeepL?
because DeepL doesnt support my country cart

A question about the get_audio_device_ids.py file

C:\Users\Terence\Downloads\LanguageLeapAI-main\LanguageLeapAI-main\src\modules>python get_audio_device_ids.py
Traceback (most recent call last):
File "C:\Users\Terence\Downloads\LanguageLeapAI-main\LanguageLeapAI-main\src\modules\get_audio_device_ids.py", line 1, in
import speech_recognition as sr
ModuleNotFoundError: No module named 'speech_recognition'

^
||
Hello everyone, am I supposed to run the file with command prompt?
I am new to programming so Im confused with stuffs
Any replies would be appreciated O7

What does this mean?

I already asked ChatGPT, and I'm stressed up of searching the source code to get that py file and even pip install doesn't work

How to set this up?

Can someone please do a step-by-step guide? I just wanna use the voice talk option, I can't seem to figure out what to do with pip and cp commands, also what do I do with docker, it's so confusing.

Voicemeter Setup

Before I try using this, I want to make sure that my voice meter is setup correctly before it potentially destroys my audio and bluescreens my pc

Problem when I execute voice_translator.py

Auto Translator auto stopping after I say anything

voice_translatior.py auto termination

please please use google translator api im from IN I cant access DeepL api keys 😢 !!

japanese audio to english subs on live, can it be done?

lets say if i were to play a japanese video on vlc or web browser and i need a way to send the audio to whisper so it can translate in in live not like and not like one mp3 auido after another but like in live i need to see english subs for an japanese audio instead of japanese i need english subs in my terminal or like you have discribed in your video and sorry for my bad english and i think it can be done but i dont know.

discord not detecting audio

I have all the program well configured but discord and obs do not detect the sound through the cable output

Application limitations

Reguarding this:

Application limitations

Some applications like Valorant for some reason does not allow open mic for team voice chat, so LanguageLeapAI will not work for in these cases, unless you hold down the push to talk button whenever you want your teammates to hear the Text-to-Speech. However, Valorant does have open mic for party voice-chat, so there should be no issue if it's used towards your party members.

We could hold down the push to talk button through code while the audio is playing. The keyboard module already imported should be able to do this (https://github.com/boppreh/keyboard#keyboardpresshotkey)

struct.error: argument out of range for voice_translator.py

I can hold down the key just fine, but when I let go I get this massive error. I am running the program using docker, and I have already double checked that the local service URLS are correct.

Exception in thread Thread-2 (process):
Traceback (most recent call last):
  File "C:\Users\kylez\AppData\Local\Programs\Python\Python310\lib\threading.py", line 1016, in _bootstrap_inner
    self.run()
  File "C:\Users\kylez\AppData\Local\Programs\Python\Python310\lib\threading.py", line 953, in run
    self._target(*self._args, **self._kwargs)
  File "C:\Users\kylez\AppData\Local\Programs\Python\Python310\lib\site-packages\keyboard\_generic.py", line 58, in process
    if self.pre_process_event(event):
  File "C:\Users\kylez\AppData\Local\Programs\Python\Python310\lib\site-packages\keyboard\__init__.py", line 213, in pre_process_event
    key_hook(event)
  File "C:\Users\kylez\AppData\Local\Programs\Python\Python310\lib\site-packages\keyboard\__init__.py", line 516, in <lambda>
    return hook_key(key, lambda e: e.event_type == KEY_DOWN or callback(e), suppress=suppress)
  File "G:\LanguageLeapAI\src\voice_translator.py", line 58, in on_release_key
    wf.writeframes(b''.join(frames))
  File "C:\Users\kylez\AppData\Local\Programs\Python\Python310\lib\wave.py", line 437, in writeframes
    self.writeframesraw(data)
  File "C:\Users\kylez\AppData\Local\Programs\Python\Python310\lib\wave.py", line 426, in writeframesraw
    self._ensure_header_written(len(data))
  File "C:\Users\kylez\AppData\Local\Programs\Python\Python310\lib\wave.py", line 467, in _ensure_header_written
    self._write_header(datasize)
  File "C:\Users\kylez\AppData\Local\Programs\Python\Python310\lib\wave.py", line 479, in _write_header
    self._file.write(struct.pack('<L4s4sLHHLLHH4s',
struct.error: argument out of range
Exception ignored in: <function Wave_write.__del__ at 0x0000017E045BF7F0>
Traceback (most recent call last):
  File "C:\Users\kylez\AppData\Local\Programs\Python\Python310\lib\wave.py", line 326, in __del__
    self.close()
  File "C:\Users\kylez\AppData\Local\Programs\Python\Python310\lib\wave.py", line 444, in close
    self._ensure_header_written(0)
  File "C:\Users\kylez\AppData\Local\Programs\Python\Python310\lib\wave.py", line 467, in _ensure_header_written
    self._write_header(datasize)
  File "C:\Users\kylez\AppData\Local\Programs\Python\Python310\lib\wave.py", line 479, in _write_header
    self._file.write(struct.pack('<L4s4sLHHLLHH4s',
struct.error: argument out of range