|
whisper: |
|
model_size: "large-v3" |
|
lang: "Automatic Detection" |
|
is_translate: false |
|
beam_size: 5 |
|
log_prob_threshold: -1 |
|
no_speech_threshold: 0.6 |
|
best_of: 5 |
|
patience: 1 |
|
condition_on_previous_text: true |
|
prompt_reset_on_temperature: 0.5 |
|
initial_prompt: null |
|
temperature: 0 |
|
compression_ratio_threshold: 2.4 |
|
chunk_length: 30 |
|
batch_size: 24 |
|
length_penalty: 1 |
|
repetition_penalty: 1 |
|
no_repeat_ngram_size: 0 |
|
prefix: null |
|
suppress_blank: true |
|
suppress_tokens: "[-1]" |
|
max_initial_timestamp: 1 |
|
word_timestamps: false |
|
prepend_punctuations: "\"'“¿([{-" |
|
append_punctuations: "\"'.。,,!!??::”)]}、" |
|
max_new_tokens: null |
|
hallucination_silence_threshold: null |
|
hotwords: null |
|
language_detection_threshold: null |
|
language_detection_segments: 1 |
|
add_timestamp: false |
|
|
|
vad: |
|
vad_filter: false |
|
threshold: 0.5 |
|
min_speech_duration_ms: 250 |
|
max_speech_duration_s: 9999 |
|
min_silence_duration_ms: 1000 |
|
speech_pad_ms: 2000 |
|
|
|
diarization: |
|
is_diarize: false |
|
hf_token: "" |
|
|
|
bgm_separation: |
|
is_separate_bgm: false |
|
model_size: "UVR-MDX-NET-Inst_HQ_4" |
|
segment_size: 256 |
|
save_file: false |
|
enable_offload: true |
|
|
|
translation: |
|
deepl: |
|
api_key: "" |
|
is_pro: false |
|
source_lang: "Automatic Detection" |
|
target_lang: "English" |
|
nllb: |
|
model_size: "facebook/nllb-200-1.3B" |
|
source_lang: null |
|
target_lang: null |
|
max_length: 200 |
|
add_timestamp: true |
|
|