diff --git a/src/ui/Forms/AudioToText/WhisperAdvanced.resx b/src/ui/Forms/AudioToText/WhisperAdvanced.resx index 1d4c415d4..a8df49be3 100644 --- a/src/ui/Forms/AudioToText/WhisperAdvanced.resx +++ b/src/ui/Forms/AudioToText/WhisperAdvanced.resx @@ -544,10 +544,10 @@ optional arguments: [--device DEVICE] [--verbose VERBOSE] -[--task {transcribe,translate}] -[--best_of BEST_OF] -[--beam_size BEAM_SIZE] -[--patience PATIENCE] +[--language_detection_threshold LANGUAGE_DETECTION_THRESHOLD] +[--language_detection_segments LANGUAGE_DETECTION_SEGMENTS] +[--temperature TEMPERATURE] [--best_of BEST_OF] +[--beam_size BEAM_SIZE] [--patience PATIENCE] [--length_penalty LENGTH_PENALTY] [--repetition_penalty REPETITION_PENALTY] [--no_repeat_ngram_size NO_REPEAT_NGRAM_SIZE] @@ -572,8 +572,7 @@ optional arguments: [--highlight_words HIGHLIGHT_WORDS] [--prepend_punctuations PREPEND_PUNCTUATIONS] [--append_punctuations APPEND_PUNCTUATIONS] -[--threads THREADS] -[--version] +[--threads THREADS] [--version] [--vad_filter VAD_FILTER] [--vad_threshold VAD_THRESHOLD] [--vad_min_speech_duration_ms VAD_MIN_SPEECH_DURATION_MS] @@ -581,24 +580,17 @@ optional arguments: [--vad_min_silence_duration_ms VAD_MIN_SILENCE_DURATION_MS] [--vad_speech_pad_ms VAD_SPEECH_PAD_MS] [--vad_window_size_samples VAD_WINDOW_SIZE_SAMPLES] -[--vad_dump] +[--vad_method {silero_v3,silero_v4,pyannote_v3,pyannote_onnx_v3,auditok,webrtc}] +[--vad_dump] [--nullify_non_speech] [--max_new_tokens MAX_NEW_TOKENS] [--chunk_length CHUNK_LENGTH] [--compute_type {default,auto,int8,int8_float16,int8_float32,int8_bfloat16,int16,float16,float32,bfloat16}] -[--batch_recursive] -[--beep_off] -[--skip] -[--checkcuda] -[--print_progress] -[--postfix] -[--check_files] -[--PR163_off] -[--hallucinations_list_off] -[--one_word {0,1,2}] -[--sentence] -[--standard] -[--standard_asia] -[--max_comma MAX_COMMA] +[--batch_recursive] [--beep_off] [--skip] +[--checkcuda] [--print_progress] [--postfix] +[--check_files] [--PR163_off] +[--hallucinations_list_off] [--alt_writer_off] +[--one_word {0,1,2}] [--sentence] [--standard] +[--standard_asia] [--max_comma MAX_COMMA] [--max_comma_cent {50,60,70,80,90,100}] [--max_gap MAX_GAP] [--max_line_width MAX_LINE_WIDTH] @@ -606,243 +598,363 @@ optional arguments: [--min_dist_to_end {0,4,5,6,7,8,9,10,11,12}] [--prompt_max {16,32,64,128,223}] [--reprompt {0,1,2}] -[--prompt_reset_on_no_end {0,1,2}] -[--ff_dump] -[--ff_track {1,2,3,4,5,6}] -[--ff_fc] -[--ff_mp3] -[--ff_sync] -[--ff_rnndn_sh] -[--ff_rnndn_xiph] -[--ff_fftdn -[0 - 97]] -[--ff_tempo -[0.5 - 2.0]] -[--ff_gate] -[--ff_speechnorm] -[--ff_loudnorm] +[--prompt_reset_on_no_end {0,1,2}] [--ff_dump] +[--ff_track {1,2,3,4,5,6}] [--ff_fc] [--ff_mp3] +[--ff_sync] [--ff_rnndn_sh] [--ff_rnndn_xiph] +[--ff_fftdn [0 - 97]] [--ff_tempo [0.5 - 2.0]] +[--ff_gate] [--ff_speechnorm] [--ff_loudnorm] [--ff_silence_suppress noise duration] -[--ff_lowhighpass] - audio -[audio ...] +[--ff_lowhighpass] [--ff_mdx_kim2] +[--mdx_chunk MDX_CHUNK] +[--mdx_device MDX_DEVICE] [--diarize] +[--diarize_device DIARIZE_DEVICE] +[--diarize_threads DIARIZE_THREADS] +[--speaker SPEAKER] +audio [audio ...] positional arguments: - audio audio file(s). You can enter a file wildcard, filelist (txt. m3u, m3u8, lst) or directory to - do batch processing. Note: non-media files in list or directory are filtered out by extension. + audio audio file(s). You can enter a file wildcard, filelist + (txt. m3u, m3u8, lst) or directory to do batch + processing. Note: non-media files in list or directory + are filtered out by extension. optional arguments: -h, --help show this help message and exit --model MODEL, -m MODEL name of the Whisper model to use (default: medium) --model_dir MODEL_DIR - the path to save model files; uses C:\git\subtitleedit\src\ui\bin\Debug\Whisper\Purfview- - Whisper-Faster\_models by default (default: None) + the path to save model files; uses C:\git\subtitleedit + \src\ui\bin\Debug\net48\Whisper\Purfview-Whisper- + Faster\_models by default (default: None) --device DEVICE, -d DEVICE - Device to use. Default is 'cuda' if CUDA device is detected, else is 'cpu'. If CUDA GPU is a - second device then set 'cuda:1'. (default: cpu) + Device to use. Default is 'cuda' if CUDA device is + detected, else is 'cpu'. If CUDA GPU is a second + device then set 'cuda:1'. (default: cpu) --output_dir OUTPUT_DIR, -o OUTPUT_DIR - directory to save the outputs. By default the same folder where the executable file is or - where media file is if --batch_recursive=True. '.'- sets to the current folder. 'source' - - sets to where media file is. (default: default) + directory to save the outputs. By default the same + folder where the executable file is or where media + file is if --batch_recursive=True. '.'- sets to the + current folder. 'source' - sets to where media file + is. (default: default) --output_format {lrc,txt,text,vtt,srt,tsv,json,all}, -f {lrc,txt,text,vtt,srt,tsv,json,all} - format of the output file; if not specified srt will be produced (default: srt) + format of the output file; if not specified srt will + be produced (default: srt) --verbose VERBOSE, -v VERBOSE whether to print out debug messages (default: False) --task {transcribe,translate} - whether to perform X->X speech recognition ('transcribe') or X->English translation - ('translate') (default: transcribe) + whether to perform X->X speech recognition + ('transcribe') or X->English translation ('translate') + (default: transcribe) --language {af,am,ar,as,az,ba,be,bg,bn,bo,br,bs,ca,cs,cy,da,de,el,en,es,et,eu,fa,fi,fo,fr,gl,gu,ha,haw,he,hi,hr,ht,hu,hy,id,is,it,ja,jw,ka,kk,km,kn,ko,la,lb,ln,lo,lt,lv,mg,mi,mk,ml,mn,mr,ms,mt,my,ne,nl,nn,no,oc,pa,pl,ps,pt,ro,ru,sa,sd,si,sk,sl,sn,so,sq,sr,su,sv,sw,ta,te,tg,th,tk,tl,tr,tt,uk,ur,uz,vi,yi,yo,yue,zh,Afrikaans,Albanian,Amharic,Arabic,Armenian,Assamese,Azerbaijani,Bashkir,Basque,Belarusian,Bengali,Bosnian,Breton,Bulgarian,Burmese,Cantonese,Castilian,Catalan,Chinese,Croatian,Czech,Danish,Dutch,English,Estonian,Faroese,Finnish,Flemish,French,Galician,Georgian,German,Greek,Gujarati,Haitian,Haitian Creole,Hausa,Hawaiian,Hebrew,Hindi,Hungarian,Icelandic,Indonesian,Italian,Japanese,Javanese,Kannada,Kazakh,Khmer,Korean,Lao,Latin,Latvian,Letzeburgesch,Lingala,Lithuanian,Luxembourgish,Macedonian,Malagasy,Malay,Malayalam,Maltese,Mandarin,Maori,Marathi,Moldavian,Moldovan,Mongolian,Myanmar,Nepali,Norwegian,Nynorsk,Occitan,Panjabi,Pashto,Persian,Polish,Portuguese,Punjabi,Pushto,Romanian,Russian,Sanskrit,Serbian,Shona,Sindhi,Sinhala,Sinhalese,Slovak,Slovenian,Somali,Spanish,Sundanese,Swahili,Swedish,Tagalog,Tajik,Tamil,Tatar,Telugu,Thai,Tibetan,Turkish,Turkmen,Ukrainian,Urdu,Uzbek,Valencian,Vietnamese,Welsh,Yiddish,Yoruba}, -l {af,am,ar,as,az,ba,be,bg,bn,bo,br,bs,ca,cs,cy,da,de,el,en,es,et,eu,fa,fi,fo,fr,gl,gu,ha,haw,he,hi,hr,ht,hu,hy,id,is,it,ja,jw,ka,kk,km,kn,ko,la,lb,ln,lo,lt,lv,mg,mi,mk,ml,mn,mr,ms,mt,my,ne,nl,nn,no,oc,pa,pl,ps,pt,ro,ru,sa,sd,si,sk,sl,sn,so,sq,sr,su,sv,sw,ta,te,tg,th,tk,tl,tr,tt,uk,ur,uz,vi,yi,yo,yue,zh,Afrikaans,Albanian,Amharic,Arabic,Armenian,Assamese,Azerbaijani,Bashkir,Basque,Belarusian,Bengali,Bosnian,Breton,Bulgarian,Burmese,Cantonese,Castilian,Catalan,Chinese,Croatian,Czech,Danish,Dutch,English,Estonian,Faroese,Finnish,Flemish,French,Galician,Georgian,German,Greek,Gujarati,Haitian,Haitian Creole,Hausa,Hawaiian,Hebrew,Hindi,Hungarian,Icelandic,Indonesian,Italian,Japanese,Javanese,Kannada,Kazakh,Khmer,Korean,Lao,Latin,Latvian,Letzeburgesch,Lingala,Lithuanian,Luxembourgish,Macedonian,Malagasy,Malay,Malayalam,Maltese,Mandarin,Maori,Marathi,Moldavian,Moldovan,Mongolian,Myanmar,Nepali,Norwegian,Nynorsk,Occitan,Panjabi,Pashto,Persian,Polish,Portuguese,Punjabi,Pushto,Romanian,Russian,Sanskrit,Serbian,Shona,Sindhi,Sinhala,Sinhalese,Slovak,Slovenian,Somali,Spanish,Sundanese,Swahili,Swedish,Tagalog,Tajik,Tamil,Tatar,Telugu,Thai,Tibetan,Turkish,Turkmen,Ukrainian,Urdu,Uzbek,Valencian,Vietnamese,Welsh,Yiddish,Yoruba} - language spoken in the audio, specify None to perform language detection (default: None) + language spoken in the audio, specify None to perform + language detection (default: None) --language_detection_threshold LANGUAGE_DETECTION_THRESHOLD - If the maximum probability of the language tokens is higher than this value, the language is - detected. (default: None) + If the maximum probability of the language tokens is + higher than this value, the language is detected. + (default: None) --language_detection_segments LANGUAGE_DETECTION_SEGMENTS - Number of segments/chunks to consider for the language detection. (default: 1) + Number of segments/chunks to consider for the language + detection. (default: 1) --temperature TEMPERATURE temperature to use for sampling (default: 0) --best_of BEST_OF, -bo BEST_OF - number of candidates when sampling with non-zero temperature (default: 5) + number of candidates when sampling with non-zero + temperature (default: 5) --beam_size BEAM_SIZE, -bs BEAM_SIZE - number of beams in beam search, only applicable when temperature is zero (default: 5) + number of beams in beam search, only applicable when + temperature is zero (default: 5) --patience PATIENCE, -p PATIENCE - optional patience value to use in beam decoding, as in https://arxiv.org/abs/2204.05424, the - default (1.0) is equivalent to conventional beam search (default: 2.0) + optional patience value to use in beam decoding, as in + https://arxiv.org/abs/2204.05424, the default (1.0) is + equivalent to conventional beam search (default: 2.0) --length_penalty LENGTH_PENALTY - optional token length penalty coefficient (alpha) as in https://arxiv.org/abs/1609.08144, uses - simple length normalization by default (default: 1.0) + optional token length penalty coefficient (alpha) as + in https://arxiv.org/abs/1609.08144, uses simple + length normalization by default (default: 1.0) --repetition_penalty REPETITION_PENALTY - Penalty applied to the score of previously generated tokens (set > 1.0 to penalize). (default: - 1.0) + Penalty applied to the score of previously generated + tokens (set > 1.0 to penalize). (default: 1.0) --no_repeat_ngram_size NO_REPEAT_NGRAM_SIZE - Prevent repetitions of ngrams with this size (set 0 to disable). (default: 0) + Prevent repetitions of ngrams with this size (set 0 to + disable). (default: 0) --suppress_blank SUPPRESS_BLANK - Suppress blank outputs at the beginning of the sampling. (default: True) + Suppress blank outputs at the beginning of the + sampling. (default: True) --suppress_tokens SUPPRESS_TOKENS - comma-separated list of token ids to suppress during sampling; '-1' will suppress most special - characters except common punctuations (default: -1) + comma-separated list of token ids to suppress during + sampling; '-1' will suppress most special characters + except common punctuations. `None` - will pass empty + list. (default: -1) --initial_prompt INITIAL_PROMPT, -prompt INITIAL_PROMPT - optional text to provide context as a prompt for the first window. Use 'None' to disable it. - Note: 'auto' and 'default' are experimental ~universal prompt presets, they work if --language - is set. (default: auto) - --prefix PREFIX Optional text to provide as a prefix for the first window (default: None) + optional text to provide context as a prompt for the + first window. Use 'None' to disable it. Note: 'auto' + and 'default' are experimental ~universal prompt + presets, they work if --language is set. (default: + auto) + --prefix PREFIX Optional text to provide as a prefix for the first + window (default: None) --condition_on_previous_text CONDITION_ON_PREVIOUS_TEXT, -condition CONDITION_ON_PREVIOUS_TEXT - if True, provide the previous output of the model as a prompt for the next window; disabling - may make the text inconsistent across windows, but the model becomes less prone to getting - stuck in a failure loop. If disabled then you may want to disable --reprompt too. (default: - True) + if True, provide the previous output of the model as a + prompt for the next window; disabling may make the + text inconsistent across windows, but the model + becomes less prone to getting stuck in a failure loop. + If disabled then you may want to disable --reprompt + too. (default: True) --prompt_reset_on_temperature PROMPT_RESET_ON_TEMPERATURE - Resets prompt if temperature is above this value. Arg has effect only if - condition_on_previous_text is True. (default: 0.5) + Resets prompt if temperature is above this value. Arg + has effect only if condition_on_previous_text is True. + (default: 0.5) --without_timestamps WITHOUT_TIMESTAMPS Only sample text tokens. (default: False) --max_initial_timestamp MAX_INITIAL_TIMESTAMP - The initial timestamp cannot be later than this. (default: 1.0) + The initial timestamp cannot be later than this. + (default: 1.0) --temperature_increment_on_fallback TEMPERATURE_INCREMENT_ON_FALLBACK, -fallback TEMPERATURE_INCREMENT_ON_FALLBACK - temperature to increase when falling back when the decoding fails to meet either of the - thresholds below. To disable fallback set it to 'None'. (default: 0.2) + temperature to increase when falling back when the + decoding fails to meet either of the thresholds below. + To disable fallback set it to 'None'. (default: 0.2) --compression_ratio_threshold COMPRESSION_RATIO_THRESHOLD - if the gzip compression ratio is higher than this value, treat the decoding as failed - (default: 2.4) + if the gzip compression ratio is higher than this + value, treat the decoding as failed (default: 2.4) --logprob_threshold LOGPROB_THRESHOLD - if the average log probability is lower than this value, treat the decoding as failed - (default: -1.0) + if the average log probability is lower than this + value, treat the decoding as failed (default: -1.0) --no_speech_threshold NO_SPEECH_THRESHOLD - if the probability of the <|nospeech|> token is higher than this value AND the decoding has - failed due to 'logprob_threshold', consider the segment as silence (default: 0.6) - --v3_offsets_off Disables custom offsets to the defaults of pseudo-vad thresholds when 'large-v3' models are in - use. Those offset were made to make 'large-v3' to hallucinate less by default. (default: - False) + if the probability of the <|nospeech|> token is higher + than this value AND the decoding has failed due to + 'logprob_threshold', consider the segment as silence + (default: 0.6) + --v3_offsets_off Disables custom offsets to the defaults of pseudo-vad + thresholds when 'large-v3' models are in use. Note: + Offsets made to combat 'large-v3' hallucinations. + (default: False) --hallucination_silence_threshold HALLUCINATION_SILENCE_THRESHOLD, -hst HALLUCINATION_SILENCE_THRESHOLD - (Experimental) When word_timestamps is True, skip silent periods longer than this threshold - (in seconds) when a possible hallucination is detected. Optimal value is somewhere between 2 - - 8 seconds. Inactive if None. (default: None) + (Experimental) When word_timestamps is True, skip + silent periods longer than this threshold (in seconds) + when a possible hallucination is detected. Optimal + value is somewhere between 2 - 8 seconds. Inactive if + None. (default: None) --hallucination_silence_th_temp {0.0,0.2,0.5,0.8,1.0}, -hst_temp {0.0,0.2,0.5,0.8,1.0} - (Experimental) Additional heuristic for '--hallucination_silence_threshold'. If temperature is - higher that this threshold then consider segment as possible hallucination ignoring the hst - score. Inactive if 1.0. (default: 1.0) - --clip_timestamps CLIP_TIMESTAMPS - Comma-separated list start,end,start,end,... timestamps (in seconds) of clips to process. The - last end timestamp defaults to the end of the file. VAD is auto-disabled. (default: 0) + (Experimental) Additional heuristic for '-- + hallucination_silence_threshold'. If temperature is + higher that this threshold then consider segment as + possible hallucination ignoring the hst score. + Inactive if 1.0. (default: 1.0) + --clip_timestamps CLIP_TIMESTAMPS, -clip CLIP_TIMESTAMPS + Comma-separated list start,end,start,end,... + timestamps (in seconds) of clips to process. The last + end timestamp defaults to the end of the file. VAD is + auto-disabled. (default: 0) --no_speech_strict_lvl {0,1,2} - (experimental) Level of stricter actions when no_speech_prob > 0.93. Use beam_size=5 if this - is enabled. Options: 0 - Disabled (do nothing), 1 - Reset propmt (see - condition_on_previous_text), 2 - Invalidate the cached encoder output (if no_speech_threshold - is not None). Arg meant to combat cases where the model is getting stuck in a failure loop or - outputs nonsense (default: 0) + (experimental) Level of stricter actions when + no_speech_prob > 0.93. Use beam_size=5 if this is + enabled. Options: 0 - Disabled (do nothing), 1 - Reset + propmt (see condition_on_previous_text), 2 - + Invalidate the cached encoder output (if + no_speech_threshold is not None). Arg meant to combat + cases where the model is getting stuck in a failure + loop or outputs nonsense (default: 0) --word_timestamps WORD_TIMESTAMPS, -wt WORD_TIMESTAMPS - Extract word-level timestamps and refine the results based on them (default: True) + Extract word-level timestamps and refine the results + based on them (default: True) --highlight_words HIGHLIGHT_WORDS, -hw HIGHLIGHT_WORDS - underline each word as it is spoken AKA karaoke in srt and vtt output formats (default: False) + underline each word as it is spoken AKA karaoke in srt + and vtt output formats (default: False) --prepend_punctuations PREPEND_PUNCTUATIONS - if word_timestamps is True, merge these punctuation symbols with the next word (default: - "'“¿([{-) + if word_timestamps is True, merge these punctuation + symbols with the next word (default: "'“¿([{-) --append_punctuations APPEND_PUNCTUATIONS - if word_timestamps is True, merge these punctuation symbols with the previous word (default: + if word_timestamps is True, merge these punctuation + symbols with the previous word (default: "'.。,，!！?？:：”)]}、) - --threads THREADS number of threads used for CPU inference; By default number of the real cores but no more that - 4 (default: 0) + --threads THREADS number of threads used for CPU inference; By default + number of the real cores but no more that 4 (default: + 0) --version Show Faster-Whisper's version number --vad_filter VAD_FILTER, -vad VAD_FILTER - Enable the voice activity detection (VAD) to filter out parts of the audio without speech. - (default: True) + Enable the voice activity detection (VAD) to filter + out parts of the audio without speech. (default: True) --vad_threshold VAD_THRESHOLD - Probabilities above this value are considered as speech. (default: 0.45) + Probabilities above this value are considered as + speech. (default: 0.45) --vad_min_speech_duration_ms VAD_MIN_SPEECH_DURATION_MS - Final speech chunks shorter min_speech_duration_ms are thrown out. (default: 350) + Final speech chunks shorter min_speech_duration_ms are + thrown out. (default: 350) --vad_max_speech_duration_s VAD_MAX_SPEECH_DURATION_S - Maximum duration of speech chunks in seconds. Longer will be split at the timestamp of the - last silence. (default: None) + Maximum duration of speech chunks in seconds. Longer + will be split at the timestamp of the last silence. + (default: None) --vad_min_silence_duration_ms VAD_MIN_SILENCE_DURATION_MS - In the end of each speech chunk time to wait before separating it. (default: 3000) + In the end of each speech chunk time to wait before + separating it. (default: 3000) --vad_speech_pad_ms VAD_SPEECH_PAD_MS - Final speech chunks are padded by speech_pad_ms each side. (default: 900) + Final speech chunks are padded by speech_pad_ms each + side. (default: 900) --vad_window_size_samples VAD_WINDOW_SIZE_SAMPLES - Size of audio chunks fed to the silero VAD model. Values other than 512, 1024, 1536 may affect - model perfomance!!! (default: 1536) - --vad_dump Dumps VAD timings to a subtitle file for inspection. (default: False) + Size of audio chunks fed to the silero VAD model. + Values other than 512, 1024, 1536 may affect model + perfomance!!! (default: 1536) + --vad_method {silero_v3,silero_v4,pyannote_v3,pyannote_onnx_v3,auditok,webrtc}, --vad_alt_method {silero_v3,silero_v4,pyannote_v3,pyannote_onnx_v3,auditok,webrtc} + Read there - 'https://github.com/Purfview/whisper- + standalone-win/discussions/231'. (default: None) + --vad_dump Dumps VAD timings to a subtitle file for inspection. + Additionaly dumps various intermediate audio files for + debug. (default: False) + --nullify_non_speech, -nullify + For dev experiments. (default: False) --max_new_tokens MAX_NEW_TOKENS - Maximum number of new tokens to generate per-chunk. (default: None) + Maximum number of new tokens to generate per-chunk. + (default: None) --chunk_length CHUNK_LENGTH - The length of audio segments. If it is not None, it will overwrite the default chunk_length of - the FeatureExtractor. (default: None) + The length of audio segments. If it is not None, it + will overwrite the default chunk_length of the + FeatureExtractor. (default: None) --compute_type {default,auto,int8,int8_float16,int8_float32,int8_bfloat16,int16,float16,float32,bfloat16}, -ct {default,auto,int8,int8_float16,int8_float32,int8_bfloat16,int16,float16,float32,bfloat16} - Type of quantization to use (see https://opennmt.net/CTranslate2/quantization.html). (default: - auto) + Type of quantization to use (see + https://opennmt.net/CTranslate2/quantization.html). + (default: auto) --batch_recursive, -br - Enables recursive batch processing. Note: If set then it changes defaults of --output_dir. + Enables recursive batch processing. Note: If set then + it changes defaults of --output_dir. (default: False) + --beep_off Disables the beep sound when operation is finished. (default: False) - --beep_off Disables the beep sound when operation is finished. (default: False) - --skip Skips media file if subtitle exists. Works if input is wildcard or directory. (default: False) - --checkcuda, -cc Returns CUDA device count. (for Subtitle Edit's internal use) - --print_progress, -pp - Prints progress bar instead of transcription. (default: False) - --postfix Adds language as a postfix to subtitle's filename. (default: False) - --check_files Checks input files for errors before passing all them for transcription. Works if input is + --skip Skips media file if subtitle exists. Works if input is wildcard or directory. (default: False) - --PR163_off (For dev experiments) Disables PR163. . (default: False) + --checkcuda, -cc Returns CUDA device count. (for Subtitle Edit's + internal use) + --print_progress, -pp + Prints progress bar instead of transcription. + (default: False) + --postfix Adds language as a postfix to subtitle's filename. + (default: False) + --check_files Checks input files for errors before passing all them + for transcription. Works if input is wildcard or + directory. (default: False) + --PR163_off (For dev experiments) Disables PR163. . (default: + False) --hallucinations_list_off - (For dev experiments) Disables hallucinations_list, allows hallucinations added to prompt. - (default: False) - --one_word {0,1,2} 0) Disabled. 1) Outputs srt and vtt subtitles with one word per line. 2) As '1', plus removes - whitespace and ensures >= 50ms for sub lines. Note: VAD may slightly reduce the accuracy of - timestamps on some lines. (default: 0) - --sentence Enables splitting lines to sentences for srt and vtt subs. Every sentence starts in the new - segment. By default meant to output whole sentence per line for better translations, but not - limited to, read about '--max_...' parameters. Note: has no effect on 'highlight_words'. - (default: False) - --standard Quick hardcoded preset to split lines in standard way. 42 chars per 2 lines with - max_comma_cent=70 and --sentence are activated automatically. (default: False) - --standard_asia Quick hardcoded preset to split lines in standard way for some Asian languages. 16 chars per 2 - lines with max_comma_cent=80 and --sentence are activated automatically. (default: False) + (For dev experiments) Disables hallucinations_list, + allows hallucinations added to prompt. (default: + False) + --alt_writer_off (For dev experiments) Forcefully disables alternative + subs writer func. (default: False) + --one_word {0,1,2} 0) Disabled. 1) Outputs srt and vtt subtitles with one + word per line. 2) As '1', plus removes whitespace and + ensures >= 50ms for sub lines. Note: VAD may slightly + reduce the accuracy of timestamps on some lines. + (default: 0) + --sentence Enables splitting lines to sentences for srt and vtt + subs. Every sentence starts in the new segment. By + default meant to output whole sentence per line for + better translations, but not limited to, read about ' + --max_...' parameters. Note: has no effect on + 'highlight_words'. (default: False) + --standard Quick hardcoded preset to split lines in standard way. + 42 chars per 2 lines with max_comma_cent=70 and + --sentence are activated automatically. (default: + False) + --standard_asia Quick hardcoded preset to split lines in standard way + for some Asian languages. 16 chars per 2 lines with + max_comma_cent=80 and --sentence are activated + automatically. (default: False) --max_comma MAX_COMMA - (requires --sentence) After this line length a comma is treated as the end of sentence. Note: - disabled if it's over or equal to --max_line_width. (default: 250) + (requires --sentence) After this line length a comma + is treated as the end of sentence. Note: disabled if + it's over or equal to --max_line_width. (default: 250) --max_comma_cent {50,60,70,80,90,100} - (requires --sentence) Percentage of --max_line_width when it starts breaking the line after - comma. Note: 100 = disabled. (default: 100) - --max_gap MAX_GAP (requires --sentence) Threshold for a gap length in seconds, longer gaps are treated as dots. - (default: 3.0) + (requires --sentence) Percentage of --max_line_width + when it starts breaking the line after comma. Note: + 100 = disabled. (default: 100) + --max_gap MAX_GAP (requires --sentence) Threshold for a gap length in + seconds, longer gaps are treated as dots. (default: + 3.0) --max_line_width MAX_LINE_WIDTH - The maximum number of characters in a line before breaking the line. (default: 1000) + The maximum number of characters in a line before + breaking the line. Note: It works with `--sentence` + too. (default: 1000) --max_line_count MAX_LINE_COUNT - The maximum number of lines in one sub segment. (default: 1) + The maximum number of lines in one sub segment. Note: + It works with `--sentence` too. (default: 1) --min_dist_to_end {0,4,5,6,7,8,9,10,11,12} - (requires --sentence) If from words like 'the', 'Mr.' and ect. to the end of line distance is - less than set then it starts in a new line. Note: 0 = disabled. (default: 0) + (requires --sentence) If from words like 'the', 'Mr.' + and ect. to the end of line distance is less than set + then it starts in a new line. Note: 0 = disabled. + (default: 0) --prompt_max {16,32,64,128,223} - (experimental) The maximum size of prompt. (default: 223) - --reprompt {0,1,2} (experimental) 0) Disabled. 1) Inserts initial_prompt after the prompt resets. 2) Ensures that - initial_prompt is present in prompt for all windows/chunks. Note: auto-disabled if - initial_prompt=None. It's similar to 'hotwords' feature. (default: 2) + (experimental) The maximum size of prompt. (default: + 223) + --reprompt {0,1,2} (experimental) 0) Disabled. 1) Inserts initial_prompt + after the prompt resets. 2) Ensures that + initial_prompt is present in prompt for all + windows/chunks. Note: auto-disabled if + initial_prompt=None. It's similar to 'hotwords' + feature. (default: 2) --prompt_reset_on_no_end {0,1,2} - (experimental) Resets prompt if there is no end of sentence in window/chunk. 0 - disabled, 1 - - looks for period, 2 - looks for period or comma. Note: it's auto-disabled if reprompt=0. - (default: 2) - --ff_dump Dumps pre-processed audio by the filters to the 16000Hz file and prevents deletion of some + (experimental) Resets prompt if there is no end of + sentence in window/chunk. 0 - disabled, 1 - looks for + period, 2 - looks for period or comma. Note: it's + auto-disabled if reprompt=0. (default: 2) + --ff_dump Dumps pre-processed audio by the filters to the + 16000Hz file and prevents deletion of some intermediate audio files. (default: False) --ff_track {1,2,3,4,5,6} - Audio track selector. 1 - selects the first audio track. (default: 1) - --ff_fc Selects only front-center channel (FC) to process. (default: False) - --ff_mp3 Audio filter: Conversion to MP3 and back. (default: False) - --ff_sync Audio filter: Stretch/squeeze samples to the given timestamps, with a maximum of 3600 samples - per second compensation. Input file must be container that support storing PTS like mp4, - mkv... (default: False) - --ff_rnndn_sh Audio filter: Suppress non-speech with GregorR's SH model using Recurrent Neural Networks. - Notes: It's more aggressive than Xiph, discards singing. (default: False) - --ff_rnndn_xiph Audio filter: Suppress non-speech with Xiph's original model using Recurrent Neural Networks. + Audio track selector. 1 - selects the first audio + track. (default: 1) + --ff_fc Selects only front-center channel (FC) to process. (default: False) - --ff_fftdn [0 - 97] Audio filter: General denoise with Fast Fourier Transform. Notes: 12 - normal strength, 0 - - disabled. (default: 0) + --ff_mp3 Audio filter: Conversion to MP3 and back. (default: + False) + --ff_sync Audio filter: Stretch/squeeze samples to the given + timestamps, with a maximum of 3600 samples per second + compensation. Input file must be container that + support storing PTS like mp4, mkv... (default: False) + --ff_rnndn_sh Audio filter: Suppress non-speech with GregorR's SH + model using Recurrent Neural Networks. Notes: It's + more aggressive than Xiph, discards singing. (default: + False) + --ff_rnndn_xiph Audio filter: Suppress non-speech with Xiph's original + model using Recurrent Neural Networks. (default: + False) + --ff_fftdn [0 - 97] Audio filter: General denoise with Fast Fourier + Transform. Notes: 12 - normal strength, 0 - disabled. + (default: 0) --ff_tempo [0.5 - 2.0] - Audio filter: Adjust audio tempo. Values below 1.0 slows down audio, above - speeds up. 1.0 = - disabled. (default: 1.0) - --ff_gate Audio filter: Reduce lower parts of a signal. (default: False) - --ff_speechnorm Audio filter: Extreme and fast speech amplification. (default: False) - --ff_loudnorm Audio filter: EBU R128 loudness normalization. (default: False) + Audio filter: Adjust audio tempo. Values below 1.0 + slows down audio, above - speeds up. 1.0 = disabled. + (default: 1.0) + --ff_gate Audio filter: Reduce lower parts of a signal. + (default: False) + --ff_speechnorm Audio filter: Extreme and fast speech amplification. + (default: False) + --ff_loudnorm Audio filter: EBU R128 loudness normalization. + (default: False) --ff_silence_suppress noise duration - Audio filter: Suppress quiet parts of audio. Takes two values. First value - noise tolerance - in decibels [-70 - 0] (0=disabled), second value - minimum silence duration in seconds [0.1 - - 10]. (default: [0, 3.0]) - --ff_lowhighpass Audio filter: Pass 50Hz - 7800 band. sinc + afir. (default: False) + Audio filter: Suppress quiet parts of audio. Takes two + values. First value - noise tolerance in decibels [-70 + - 0] (0=disabled), second value - minimum silence + duration in seconds [0.1 - 10]. (default: [0, 3.0]) + --ff_lowhighpass Audio filter: Pass 50Hz - 7800 band. sinc + afir. + (default: False) + --ff_mdx_kim2 Audio filter: High quality vocals extraction. MDX-Net + 'Kim_Vocal_2' model made by KimberleyJensen. Notes: + It's better than 'HT Demucs v4 FT', first in the + filters chain, recommended to use on movies and + series. (default: False) + --mdx_chunk MDX_CHUNK + Chunk size in seconds for MDX-Net filter. Notes: + Smaller is using less memory, but can be slower and + produce a bit lower quality. (default: 15) + --mdx_device MDX_DEVICE + Device to use for MDX-Net filter. Default is 'cuda' if + CUDA device is detected, else is 'cpu'. If CUDA GPU is + a second device then set 'cuda:1'. (default: cpu) + --diarize Enable diarization. (default: False) + --diarize_device DIARIZE_DEVICE + Device to use for '--diarize'. Default is 'cuda' if + CUDA device is detected, else is 'cpu'. If CUDA GPU is + a second device then set 'cuda:1'. (default: cpu) + --diarize_threads DIARIZE_THREADS + --speaker SPEAKER To replace 'SPEAKER' string with your own word. + (default: SPEAKER) \ No newline at end of file