From 0b85e8c40127902e5ed0557ea9e2c42df2a1e005 Mon Sep 17 00:00:00 2001 From: Georgi Gerganov Date: Sun, 15 Jan 2023 11:36:20 +0200 Subject: [PATCH] Update README.md --- README.md | 51 ++++++++++++++++++++++++++++++--------------------- 1 file changed, 30 insertions(+), 21 deletions(-) diff --git a/README.md b/README.md index 448e758..e9cbd1d 100644 --- a/README.md +++ b/README.md @@ -89,27 +89,36 @@ c++ -I. -I./examples -O3 -std=c++11 -pthread examples/main/main.cpp whisper.o gg usage: ./main [options] file0.wav file1.wav ... options: - -h, --help [default] show this help message and exit - -t N, --threads N [4 ] number of threads to use during computation - -p N, --processors N [1 ] number of processors to use during computation - -ot N, --offset-t N [0 ] time offset in milliseconds - -on N, --offset-n N [0 ] segment index offset - -d N, --duration N [0 ] duration of audio to process in milliseconds - -mc N, --max-context N [-1 ] maximum number of text context tokens to store - -ml N, --max-len N [0 ] maximum segment length in characters - -wt N, --word-thold N [0.01 ] word timestamp probability threshold - -su, --speed-up [false ] speed up audio by x2 (reduced accuracy) - -tr, --translate [false ] translate from source language to english - -otxt, --output-txt [false ] output result in a text file - -ovtt, --output-vtt [false ] output result in a vtt file - -osrt, --output-srt [false ] output result in a srt file - -owts, --output-words [false ] output script for generating karaoke video - -ps, --print-special [false ] print special tokens - -pc, --print-colors [false ] print colors - -nt, --no-timestamps [true ] do not print timestamps - -l LANG, --language LANG [en ] spoken language - -m FNAME, --model FNAME [models/ggml-base.en.bin] model path - -f FNAME, --file FNAME [ ] input WAV file path + -h, --help [default] show this help message and exit + -t N, --threads N [4 ] number of threads to use during computation + -p N, --processors N [1 ] number of processors to use during computation + -ot N, --offset-t N [0 ] time offset in milliseconds + -on N, --offset-n N [0 ] segment index offset + -d N, --duration N [0 ] duration of audio to process in milliseconds + -mc N, --max-context N [-1 ] maximum number of text context tokens to store + -ml N, --max-len N [0 ] maximum segment length in characters + -bo N, --best-of N [5 ] number of best candidates to keep + -bs N, --beam-size N [-1 ] beam size for beam search + -wt N, --word-thold N [0.01 ] word timestamp probability threshold + -et N, --entropy-thold N [2.40 ] entropy threshold for decoder fail + -lpt N, --logprob-thold N [-1.00 ] log probability threshold for decoder fail + -su, --speed-up [false ] speed up audio by x2 (reduced accuracy) + -tr, --translate [false ] translate from source language to english + -di, --diarize [false ] stereo audio diarization + -otxt, --output-txt [false ] output result in a text file + -ovtt, --output-vtt [false ] output result in a vtt file + -osrt, --output-srt [false ] output result in a srt file + -owts, --output-words [false ] output script for generating karaoke video + -ocsv, --output-csv [false ] output result in a CSV file + -ps, --print-special [false ] print special tokens + -pc, --print-colors [false ] print colors + -pp, --print-progress [false ] print progress + -nt, --no-timestamps [true ] do not print timestamps + -l LANG, --language LANG [en ] spoken language ('auto' for auto-detect) + --prompt PROMPT [ ] initial prompt + -m FNAME, --model FNAME [models/ggml-base.en.bin] model path + -f FNAME, --file FNAME [ ] input WAV file path + bash ./models/download-ggml-model.sh base.en Downloading ggml model base.en ...