whisper-ctranslate2-remote-api 0.4.5

Whisper command line client that uses a remote CTranslate2/faster-whisper instance via a remote API call

Introduction

Whisper command line client compatible with original OpenAI client based on CTranslate2.

It uses CTranslate2 and Faster-whisper Whisper implementation that is up to 4 times faster than openai/whisper for the same accuracy while using less memory.

Goals of the project:

• Provide an easy way to use the CTranslate2 Whisper implementation
• Ease the migration for people using OpenAI Whisper CLI

Installation

To install the latest stable version, just type:

pip install -U whisper-ctranslate2

Alternatively, if you are interested in the latest development (non-stable) version from this repository, just type:

pip install git+https://github.com/Softcatala/whisper-ctranslate2

CPU and GPU support

GPU and CPU support are provided by CTranslate2.

It has compatibility with x86-64 and AArch64/ARM64 CPU and integrates multiple backends that are optimized for these platforms: Intel MKL, oneDNN, OpenBLAS, Ruy, and Apple Accelerate.

GPU execution requires the NVIDIA libraries cuBLAS 11.x and cuDNN 8.x to be installed on the system. Please refer to the CTranslate2 documentation

Install on ubuntu: sudo apt install nvidia-cudnn

By default the best hardware available is selected for inference. You can use the options --device and --device_index to control manually the selection.

Usage

Same command line as OpenAI Whisper.

To transcribe:

whisper-ctranslate2 inaguracio2011.mp3 --model medium

To translate:

whisper-ctranslate2 inaguracio2011.mp3 --model medium --task translate

Whisper translate task translates the transcription from the source language to English (the only target language supported).

Additionally using:

whisper-ctranslate2 --help

All the supported options with their help are shown.

CTranslate2 specific options

On top of the OpenAI Whisper command line options, there are some specific options provided by CTranslate2 or whiper-ctranslate2.

Quantization

--compute_type option which accepts default,auto,int8,int8_float16,int16,float16,float32 values indicates the type of quantization to use. On CPU int8 will give the best performance:

whisper-ctranslate2 myfile.mp3 --compute_type int8

Loading the model from a directory

--model_directory option allows to specify the directory from which you want to load a CTranslate2 Whisper model. For example, if you want to load your own quantified Whisper model version or using your own Whisper fine-tunned version. The model must be in CTranslate2 format.

Using Voice Activity Detection (VAD) filter

--vad_filter option enables the voice activity detection (VAD) to filter out parts of the audio without speech. This step uses the Silero VAD model:

whisper-ctranslate2 myfile.mp3 --vad_filter True

The VAD filter accepts multiple additional options to determine the filter behavior:

--vad_threshold VALUE (float)

Probabilities above this value are considered as speech.

--vad_min_speech_duration_ms (int)

Final speech chunks shorter min_speech_duration_ms are thrown out.

--vad_max_speech_duration_s VALUE (int)

Maximum duration of speech chunks in seconds. Longer will be split at the timestamp of the last silence.

Print colors

--print_colors True options prints the transcribed text using an experimental color coding strategy based on whisper.cpp to highlight words with high or low confidence:

whisper-ctranslate2 myfile.mp3 --print_colors True

Live transcribe from your microphone

--live_transcribe True option activates the live transcription mode from your microphone:

whisper-ctranslate2 --live_transcribe True --language en

https://user-images.githubusercontent.com/309265/231533784-e58c4b92-e9fb-4256-b4cd-12f1864131d9.mov

Requirements for "pip install pyaudio": sudo apt-get install python3.10-dev libasound-dev portaudio19-dev libportaudio2 libportaudiocpp0

sudo apt-get install python3-pyaudio 610 pip install pyaudio 611 sudo apt-get purge python3-pyaudio 612 pip install pyaudio 613 sudo apt-get install python3.10-dev 614 pip install pyaudio 615 sudo apt-get install libasound-dev 616 pip install pyaudio 617 sudo apt-get purge libasound-dev 618 sudo apt autoremove 619 sudo apt-get install libasound-dev 620 pip install pyaudio 621 sudo apt-get install python-pyaudio 622 sudo apt-get install python3-pyaudio 623 pip install pyaudio 624 pip install portaudio 625 sudo apt-get install portaudio 626 sudo apt-get install libasound-dev portaudio19-dev libportaudio2 libportaudiocpp0 627 pip install pyaudio 628 python list_input_sounddevice.py

Diarization (speaker identification)

There is experimental diarization support using pyannote.audio to identify speakers. At the moment, the support is a segment level.

To enable diarization you need to follow these steps:

1. Install pyannote.audio with pip install pyannote.audio
2. Accept pyannote/segmentation-3.0 user conditions
3. Accept pyannote/speaker-diarization-3.1 user conditions
4. Create access token at hf.co/settings/tokens.

And then execute passing the HuggingFace API token as parameter to enable diarization:

whisper-ctranslate2 --hf_token YOUR_HF_TOKEN

and then the name of the speaker is added in the output files (e.g. JSON, VTT and STR files):

[SPEAKER_00]: There is a lot of people in this room

The option --speaker_name SPEAKER_NAME allows to use your own string to identify the speaker.

Need help?

Check our frequently asked questions for common questions.

Contact

Jordi Mas [e-mail]