ExternalVendorCode/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/whisper.cpp.git synced 2025-02-21 09:21:49 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

readme : update help (#1560)

Browse Source
This commit is contained in:
Hang 2023-11-27 18:04:08 +08:00 committed by GitHub
parent bfacd9f8ce
commit 641f2f4282
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 17 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
README.md
View File

@ -110,8 +110,8 @@ options:
-mc N, --max-context N [-1 ] maximum number of text context tokens to store -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 -ml N, --max-len N [0 ] maximum segment length in characters
-sow, --split-on-word [false ] split on word rather than on token -sow, --split-on-word [false ] split on word rather than on token
-bo N, --best-of N [2 ] number of best candidates to keep -bo N, --best-of N [5 ] number of best candidates to keep
-bs N, --beam-size N [-1 ] beam size for beam search -bs N, --beam-size N [5 ] beam size for beam search
-wt N, --word-thold N [0.01 ] word timestamp probability threshold -wt N, --word-thold N [0.01 ] word timestamp probability threshold
-et N, --entropy-thold N [2.40 ] entropy threshold for decoder fail -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 -lpt N, --logprob-thold N [-1.00 ] log probability threshold for decoder fail
@ -128,6 +128,7 @@ options:
-fp, --font-path [/System/Library/Fonts/Supplemental/Courier New Bold.ttf] path to a monospace font for karaoke video -fp, --font-path [/System/Library/Fonts/Supplemental/Courier New Bold.ttf] path to a monospace font for karaoke video
-ocsv, --output-csv [false ] output result in a CSV file -ocsv, --output-csv [false ] output result in a CSV file
-oj, --output-json [false ] output result in a JSON file -oj, --output-json [false ] output result in a JSON file
-ojf, --output-json-full [false ] include more information in the JSON file
-of FNAME, --output-file FNAME [ ] output file path (without file extension) -of FNAME, --output-file FNAME [ ] output file path (without file extension)
-ps, --print-special [false ] print special tokens -ps, --print-special [false ] print special tokens
-pc, --print-colors [false ] print colors -pc, --print-colors [false ] print colors
@ -139,7 +140,8 @@ options:
-m FNAME, --model FNAME [models/ggml-base.en.bin] model path -m FNAME, --model FNAME [models/ggml-base.en.bin] model path
-f FNAME, --file FNAME [ ] input WAV file path -f FNAME, --file FNAME [ ] input WAV file path
-oved D, --ov-e-device DNAME [CPU ] the OpenVINO device used for encode inference -oved D, --ov-e-device DNAME [CPU ] the OpenVINO device used for encode inference
-ls, --log-score [false ] log best decoder scores of token -ls, --log-score [false ] log best decoder scores of tokens
-ng, --no-gpu [false ] disable GPU
bash ./models/download-ggml-model.sh base.en bash ./models/download-ggml-model.sh base.en

15
examples/main/README.md
View File

@ -17,28 +17,37 @@ options:
-d N, --duration N [0 ] duration of audio to process in milliseconds -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 -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 -ml N, --max-len N [0 ] maximum segment length in characters
-sow, --split-on-word [false ] split on word rather than on token
-bo N, --best-of N [5 ] number of best candidates to keep -bo N, --best-of N [5 ] number of best candidates to keep
-bs N, --beam-size N [-1 ] beam size for beam search -bs N, --beam-size N [5 ] beam size for beam search
-wt N, --word-thold N [0.01 ] word timestamp probability threshold -wt N, --word-thold N [0.01 ] word timestamp probability threshold
-et N, --entropy-thold N [2.40 ] entropy threshold for decoder fail -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 -lpt N, --logprob-thold N [-1.00 ] log probability threshold for decoder fail
-su, --speed-up [false ] speed up audio by x2 (reduced accuracy) -debug, --debug-mode [false ] enable debug mode (eg. dump log_mel)
-tr, --translate [false ] translate from source language to english -tr, --translate [false ] translate from source language to english
-di, --diarize [false ] stereo audio diarization -di, --diarize [false ] stereo audio diarization
-tdrz, --tinydiarize [false ] enable tinydiarize (requires a tdrz model)
-nf, --no-fallback [false ] do not use temperature fallback while decoding -nf, --no-fallback [false ] do not use temperature fallback while decoding
-otxt, --output-txt [false ] output result in a text file -otxt, --output-txt [false ] output result in a text file
-ovtt, --output-vtt [false ] output result in a vtt file -ovtt, --output-vtt [false ] output result in a vtt file
-osrt, --output-srt [false ] output result in a srt file -osrt, --output-srt [false ] output result in a srt file
-olrc, --output-lrc [false ] output result in a lrc file
-owts, --output-words [false ] output script for generating karaoke video -owts, --output-words [false ] output script for generating karaoke video
-fp, --font-path [/System/Library/Fonts/Supplemental/Courier New Bold.ttf] path to a monospace font for karaoke video
-ocsv, --output-csv [false ] output result in a CSV file -ocsv, --output-csv [false ] output result in a CSV file
-oj, --output-json [false ] output result in a JSON file -oj, --output-json [false ] output result in a JSON file
-ojf, --output-json-full [false ] include more information in the JSON file
-of FNAME, --output-file FNAME [ ] output file path (without file extension) -of FNAME, --output-file FNAME [ ] output file path (without file extension)
-ps, --print-special [false ] print special tokens -ps, --print-special [false ] print special tokens
-pc, --print-colors [false ] print colors -pc, --print-colors [false ] print colors
-pp, --print-progress [false ] print progress -pp, --print-progress [false ] print progress
-nt, --no-timestamps [true ] do not print timestamps -nt, --no-timestamps [false ] do not print timestamps
-l LANG, --language LANG [en ] spoken language ('auto' for auto-detect) -l LANG, --language LANG [en ] spoken language ('auto' for auto-detect)
-dl, --detect-language [false ] exit after automatically detecting language
--prompt PROMPT [ ] initial prompt --prompt PROMPT [ ] initial prompt
-m FNAME, --model FNAME [models/ggml-base.en.bin] model path -m FNAME, --model FNAME [models/ggml-base.en.bin] model path
-f FNAME, --file FNAME [ ] input WAV file path -f FNAME, --file FNAME [ ] input WAV file path
-oved D, --ov-e-device DNAME [CPU ] the OpenVINO device used for encode inference
-ls, --log-score [false ] log best decoder scores of tokens
-ng, --no-gpu [false ] disable GPU
``` ```