stream-translator-gpt
Command line utility to transcribe or translate audio from livestreams in real time. Uses yt-dlp to get livestream URLs from various services and Whisper / Faster-Whisper for transcription.
This fork optimized the audio slicing logic based on VAD, introduced GPT API / Gemini API to support language translation beyond English, and supports input from the audio devices.
Try it on Colab:
Prerequisites
Linux or Windows:
- Python >= 3.8 (Recommend >= 3.10)
- Install CUDA on your system. You can check the installed CUDA version with
nvcc --version. - Install cuDNN to your CUDA dir if you want to use Faseter-Whisper.
- Install PyTorch (with CUDA) to your Python.
- Create a Google API key if you want to use Gemini API for translation. (Recommend, Free 60 requests / minute)
- Create a OpenAI API key if you want to use Whisper API for transcription or GPT API for translation.
If you are in Windows, you also need to:
- Install and add ffmpeg to your PATH.
- Install yt-dlp and add it to your PATH.
Installation
Install release version from PyPI (Recommend):
pip install stream-translator-gpt
stream-translator-gpt
or
Clone master version code from Github:
git clone https://github.com/ionic-bond/stream-translator-gpt.git
pip install -r ./stream-translator-gpt/requirements.txt
python3 ./stream-translator-gpt/translator.py
Usage
-
Transcribe live streaming (default use Whisper):
stream-translator-gpt {URL} --model large --language {input_language} -
Transcribe by Faster Whisper:
stream-translator-gpt {URL} --model large --language {input_language} --use_faster_whisper -
Transcribe by Whisper API:
stream-translator-gpt {URL} --language {input_language} --use_whisper_api --openai_api_key {your_openai_key} -
Translate to other language by Gemini:
stream-translator-gpt {URL} --model large --language ja --gpt_translation_prompt "Translate from Japanese to Chinese" --google_api_key {your_google_key} -
Translate to other language by GPT:
stream-translator-gpt {URL} --model large --language ja --gpt_translation_prompt "Translate from Japanese to Chinese" --openai_api_key {your_openai_key} -
Using Whisper API and Gemini at the same time:
stream-translator-gpt {URL} --model large --language ja --use_whisper_api --openai_api_key {your_openai_key} --gpt_translation_prompt "Translate from Japanese to Chinese" --google_api_key {your_google_key} -
Local video/audio file as input:
stream-translator-gpt /path/to/file --model large --language {input_language} -
Computer microphone as input:
stream-translator-gpt device --model large --language {input_language}Will use the system's default audio device as input.
If you want to use another audio input device,
stream-translator-gpt device --print_all_devicesget device index and then run the CLI with--device_index {index}.If you want to use the audio output of another program as input, you need to enable stereo mix.
-
Sending result to Cqhttp:
stream-translator-gpt {URL} --model large --language {input_language} --cqhttp_url {your_cqhttp_url} --cqhttp_token {your_cqhttp_token} -
Sending result to Discord:
stream-translator-gpt {URL} --model large --language {input_language} --discord_webhook_url {your_discord_webhook_url}
1 maintainer
Metadata
1 maintainer
Release files for stream-translator-gpt 2024.3.22
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| stream-translator-gpt-2024.3.22.tar.gz | 1.1 MB | Without provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| stream_translator_gpt-2024.3.22-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 2.3 MB
Release files / stream-translator-gpt-2024.3.22.tar.gz
| Download URL | stream-translator-gpt-2024.3.22.tar.gz |
|---|---|
| Size | 1.1 MB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
640b7053ec799519687fd5f3bbb9865440f3d1517928c5d9c5789e278c40a92d
|
|
BLAKE2b-256 checksum How to use checksums |
ef5d10ceeac5c3643a3f8b71592b41a3ca3dbbab5c5b53b0a3bd5d4def27f592
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/5.0.0 CPython/3.10.12
|
Release files / stream_translator_gpt-2024.3.22-py3-none-any.whl
| Download URL | stream_translator_gpt-2024.3.22-py3-none-any.whl |
|---|---|
| Size | 1.1 MB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
0271a4de5c4f5cc152f95c731c9844829fc04a5beebbd367fc642e17256945e7
|
|
BLAKE2b-256 checksum How to use checksums |
bd75e3a0f3a7daa142c5864b91121aa02974676e8d380d94dfdd180afd4cd19f
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/5.0.0 CPython/3.10.12
|
Security for stream-translator-gpt 2024.3.22
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.
