https://github.com/paddy41601/faster-whisper-cli
A command-line interface wrapper for Faster Whisper
https://github.com/paddy41601/faster-whisper-cli
faster-whisper openai quantization speech-recognition speech-to-text transformer whisper
Last synced: 7 months ago
JSON representation
A command-line interface wrapper for Faster Whisper
- Host: GitHub
- URL: https://github.com/paddy41601/faster-whisper-cli
- Owner: paddy41601
- Created: 2023-05-13T08:48:47.000Z (over 2 years ago)
- Default Branch: master
- Last Pushed: 2023-12-14T07:30:20.000Z (almost 2 years ago)
- Last Synced: 2024-10-24T10:08:05.633Z (12 months ago)
- Topics: faster-whisper, openai, quantization, speech-recognition, speech-to-text, transformer, whisper
- Language: Python
- Homepage:
- Size: 1.31 MB
- Stars: 8
- Watchers: 1
- Forks: 2
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Faster Whisper CLI
Faster Whisper CLI is a Python package that provides an easy-to-use interface for generating transcriptions and translations from audio files using pre-trained Transformer-based models.
This CLI version of Faster Whisper allows you to quickly transcribe or translate an audio file using a command-line interface.
## Installation
You can install Faster Whisper CLI using `pip`:
```
pip install faster-whisper-cli
```
## Usage
To use Faster Whisper CLI, simply run the `faster-whisper` command followed by the path to the input audio file:
```
faster-whisper path/to/audio.wav
```
This will transcribe the audio file using the default settings and print the output to the console.
You can also specify various options to customize the transcription process:
```
usage: faster-whisper [-h] [-o OUTPUT] [--language LANGUAGE] [--task TASK]
[--beam_size BEAM_SIZE] [--best_of BEST_OF]
[--patience PATIENCE]
[--length_penalty LENGTH_PENALTY]
[--temperature TEMPERATURE [TEMPERATURE ...]]
[--compression_ratio_threshold COMPRESSION_RATIO_THRESHOLD]
[--log_prob_threshold LOG_PROB_THRESHOLD]
[--no_speech_threshold NO_SPEECH_THRESHOLD]
[--condition_on_previous_text CONDITION_ON_PREVIOUS_TEXT]
[--initial_prompt INITIAL_PROMPT] [--prefix PREFIX]
[--suppress_blank SUPPRESS_BLANK]
[--suppress_tokens SUPPRESS_TOKENS [SUPPRESS_TOKENS ...]]
[--without_timestamps WITHOUT_TIMESTAMPS]
[--max_initial_timestamp MAX_INITIAL_TIMESTAMP]
[--word_timestamps WORD_TIMESTAMPS]
[--prepend_punctuations PREPEND_PUNCTUATIONS]
[--append_punctuations APPEND_PUNCTUATIONS]
[--vad_filter VAD_FILTER] [--model_size_or_path MODEL_SIZE_OR_PATH]
[--device DEVICE] [--device_index DEVICE_INDEX [DEVICE_INDEX ...]]
[--compute_type COMPUTE_TYPE] [--cpu_threads CPU_THREADS]
[--num_workers NUM_WORKERS]
audio
```