stream-translator-gpt 2024.3.6

Command line tool to transcribe & translate audio from livestreams in real time

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 OpenAI's Whisper for transcription/translation.

This fork optimized the audio slicing logic based on VAD, introduced OpenAI's GPT API / Google's Gemini API to support language translation beyond English, and supports getting audio from the devices.

Try it on Colab:

Prerequisites

Linux or Windows:

1. Python >= 3.8 (Recommend >= 3.10)
2. Install CUDA on your system. You can check the installed CUDA version with nvcc --version.
3. Install cuDNN to your CUDA dir if you want to use faseter-whisper.
4. Install PyTorch (with CUDA) to your Python.
5. Create a Google API key if you want to use Gemini API for translation. (Recommend, Free 60 requests / minute)
6. 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:

1. Install and add ffmpeg to your PATH.
2. 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_devices get 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}

All options

Option	Default Value	Description
Input Options
URL		The URL of the stream. If a local file path is filled in, it will be used as input. If fill in "device", the input will be obtained from your PC device.
--format	wa*	Stream format code, this parameter will be passed directly to yt-dlp.
--cookies		Used to open member-only stream, this parameter will be passed directly to yt-dlp.
--direct_url		Set this flag to pass the URL directly to ffmpeg. Otherwise, yt-dlp is used to obtain the stream URL.
--device_index		The index of the device that needs to be recorded. If not set, the system default recording device will be used.
Audio Slicing Options
--frame_duration	0.1	The unit that processes live streaming data in seconds.
--continuous_no_speech_threshold	0.8	Slice if there is no speech for a continuous period in second.
--min_audio_length	3.0	Minimum slice audio length in seconds.
--max_audio_length	30.0	Maximum slice audio length in seconds.
--prefix_retention_length	0.8	The length of the retention prefix audio during slicing.
--vad_threshold	0.5	The threshold of Voice activity detection. if the speech probability of a frame is higher than this value, then this frame is speech.
Transcription Options
--model	small	Select model size. See here for available models.
--task	transcribe	Whether to transcribe the audio (keep original language) or translate to english.
--language	auto	Language spoken in the stream. See here for available languages.
--beam_size	5	Number of beams in beam search. Set to 0 to use greedy algorithm instead (faster but less accurate).
--best_of	5	Number of candidates when sampling with non-zero temperature.
--use_faster_whisper		Set this flag to use Faster Whisper implementation instead of the original OpenAI implementation
--use_whisper_api		Set this flag to use OpenAI Whisper API instead of the original local Whipser.
--whisper_filters	emoji_filter	Filters apply to whisper results, separated by ",".
Translation Options
--openai_api_key		OpenAI API key if using GPT translation / Whisper API.
--google_api_key		Google API key if using Gemini translation.
--gpt_model	gpt-3.5-turbo	GPT model name, gpt-3.5-turbo or gpt-4. (If using Gemini, not need to change this)
--gpt_translation_prompt		If set, will translate the result text to target language via GPT / Gemini API (According to which API key is filled in). Example: "Translate from Japanese to Chinese"
--gpt_translation_history_size	0	The number of previous messages sent when calling the GPT / Gemini API. If the history size is 0, the translation will be run parallelly. If the history size > 0, the translation will be run serially.
--gpt_translation_timeout	15	If the GPT / Gemini translation exceeds this number of seconds, the translation will be discarded.
--gpt_base_url		Customize the API endpoint of GPT.
--retry_if_translation_fails		Retry when translation times out/fails. Used to generate subtitles offline.
Output Options
--output_timestamps		Output the timestamp of the text when outputting the text.
--hide_transcribe_result		Hide the result of Whisper transcribe.
--cqhttp_url		If set, will send the result text to the cqhttp server.
--cqhttp_token		Token of cqhttp, if it is not set on the server side, it does not need to fill in.

Contact me

Telegram: @ionic_bond

Donate

PayPal