pyVideoTrans

Appearance

Explanation of Advanced Settings Options ​

In the top menu -- Tools/Options -- Advanced Options, you can customize various parameters for finer control. See the image below.

【Common】 ​

  • Software interface language: Set the software's interface language. Requires a restart to take effect.

  • Countdown for single video translation pause: Countdown in seconds for a single video translation.

  • Set output directory: Directory to save results (STT, TTS, TransSubtitles). Defaults to the 'output' folder.

  • Number of retries after failure: Number of retries after failure

  • LLM re-segmentation How many subtitles are sent each time: When re-segmenting sentences in the LLM large model, the number of subtitles se nt each time is important. A larger value results in better sentence segmentation. Sending all subtitles at once is optimal, but this is limited by the maximum output token and context (max_token). An excessively long input may exceed the AI limit and fail. The default is 20 subtitles.

  • AI provider for LLM re-segmentation: AI provider for LLM re-segmentation, supports 'OpenAI ChatGPT' or 'DeepSeek'.

  • Disable desktop notifications: Disable desktop notifications for task completion or failure.

  • Translating batches, quantity per batch: When translating in batches, set the number of lines to translate simultaneously in each batch he re.

  • Show all parameters?: To avoid confusion caused by too many parameters, most parameters are hidden by default on the main interface. Selec ting this option will switch to displaying all parameters by default.

  • Number of CPU tasks[restart]: Process Maximum for CPU

  • Number of GPU tasks[restart]: The number of GPU tasks that can be executed simultaneously should be set to 1 unless the video memory is gr eater than 24GB.

  • Multi-GPU mode[restart]: If you have multiple graphics cards with identical video memory, you can enable this option and set the above opt ion to 2 or the number of graphics cards.

【Video Output】 ​

  • Video output quality control (CRF): Constant Rate Factor (CRF) for video quality. 0=lossless (huge file), 51=low quality (small file).

  • Output video compression preset: Controls the encoding speed vs. quality balance (e.g., ultrafast, medium, slow). Faster means larger file s.

  • H.264/H.265 encoding: Video codec: libx264 (better compatibility) or libx265 (higher compression).

  • Output video format (mp4/mkv): Output video format (mp4/mkv)

  • Variable frame rate (vfr)/fixed frame rate (cfr): When there is slow-motion video processing, variable frame rate (VRF) works better, whil e fixed frame rate (CFR) has better compatibility.

  • Force software video encoding?: Force software encoding (slower but more compatible). Hardware encoding is preferred by default.

  • ffmpeg decode video use cuda: When compositing videos, prioritize hard decoding; it's fast but prone to errors.

  • Custom FFmpeg command arguments: Custom FFmpeg command arguments, added before the output file argument.

【ASR Settings】 ​

  • Select VAD: Select VAD

  • VAD: Speech probability threshold: VAD: Minimum probability for an audio chunk to be considered speech.

  • no speech threshold: no speech threshold

  • VAD:max speech duration(s): VAD: Maximum duration (s) of a single speech segment before splitting.

  • VAD:Min silence duration for split(ms): VAD: Minimum silence duration (ms) to mark the end of a segment.

  • Recognition(2): max duration(s): Maximum speech duration (seconds) during secondary recognition. Limits the maximum length of a single spe ech segment. Forced segmentation occurs if this length is exceeded. Enter a number in seconds.

  • Recognition(2): min duration(ms): Shortest speech duration (milliseconds) during secondary recognition. If a subtitle's duration is less t han this value in milliseconds, attempt to merge it into an adjacent subtitle. Unit: milliseconds.

  • VAD:min speech duration(ms): If a subtitle's duration is less than this value in milliseconds, attempt to merge it into an adjacent subtit le.

  • Short sub will be merged: Short subtitles will only be merged if this option is selected

  • Whisper model Pre-segmented audio: Should we pre-segment the speech using VAD before sending it to the Whisper model for recognition? If using cloned voice-over characters, please select this option and set the shortest speech length to 3000 and the maximum speech length to 10 to improve the reliability of the voice cloning.

  • Model for speaker separation: The model used for speaker separation. The default is the built-in model, supporting both Chinese and Englis h. Pyannote is optional. If selected, you must have a token from https://huggingface.co and agree to the Pyannote licensing agreement. For details, please visit the URL for a tutorial: https://pvt9.com/shuohuaren

  • Your token from huggingface.co: Enter your token from huggingface.co. Otherwise, you cannot use Pyannote speaker separation. For details, please see the tutorial: https://pvt9.com/shuohuaren

  • Compute data type: Compute type for faster-whisper (e.g., int8, float16, float32).

  • Recognition accuracy (beam_size): Beam size for transcription (1-5). Higher is more accurate but uses more VRAM.

  • Recognition accuracy (best_of): Best-of for transcription (1-5). Higher is more accurate but uses more VRAM.

  • Enable context awareness: Condition on previous text for better context (uses more GPU, may cause repetition).

  • temperature: temperature

  • repetition penalty: Increasing this value helps reduce repetitions

  • compression ratio threshold: Decrease this value helps reduce repetitions

  • hotwords: hotwords

  • faster-whisper models: Comma-separated list of model names for faster-whisper modes.

  • whisper.cpp models: Comma-separated list of model names for whisper.cpp mode.

  • Gemini speech recognition batch slice count: Number of audio slices per request for Gemini recognition. Larger values improve accuracy but increase failure rate.

  • Convert Traditional to Simplified Chinese subtitles: Force conversion of recognized Traditional Chinese to Simplified Chinese.

  • Remove punctuation at end subtitles?: Remove punctuation at the end of subtitles?

  • Cloud API pauses after each recognition/Seconds: The number of seconds the cloud API pauses after each recognition to prevent exceeding th e frequency limit.

【Translation】 ​

  • Batch size (lines) for traditional translation: Number of subtitle lines per request for traditional translation.

  • Batch size (lines) for AI translation: Number of subtitle lines per request for AI translation.

  • Pause (s) after each translation request: Delay (in seconds) between translation requests to prevent rate-limiting.

  • Send full SRT format for AI translation: Send full SRT format content when using AI translation.

  • AI temperature for translation subtitles: AI models temperature,default is 1.0

  • AI translation channel translates all lines of the subtitles in one go.: AI translation channel translates all lines of subtitles in one g o, providing the best translation quality. [Important Note]

  1. Must use an advanced model that supports extremely long context (online AI flagship model).
  2. Feedback may be slow, manifesting as a delay in data return..

【Dubbing】 ​

  • Concurrent dubbing threads: Number of concurrent threads for dubbing.

  • Pause (s) after each dubbing request: Delay (in seconds) between dubbing requests to prevent rate-limiting.

  • Remove the mute buffer each subtitle audio: Remove the mute buffer before and after each subtitle audio. Selecting this option will improv e audio-visual synchronization, but may make the ending feel rushed.

  • Save dubbed audio for each subtitle line: Save the dubbed audio for each individual subtitle line.

  • Text Text normalization: Text normalization before dubbing

  • The higher concurrent of EdgeTTS: The higher the concurrent voice-over capacity of the EdgeTTS channel, the faster the speed, but rate thr ottling may fail.

  • Retries after EdgeTTS failure: Number of retries after EdgeTTS channel failure

  • ChatTTS voice timbre value: ChatTTS voice timbre value.

  • Threads nums for separation: The more threads used for separation of human and background voices, the faster the process, but the more res ources it consumes.

  • BGM separation model: Select the model used when separating background noise.

【Alignment】 ​

  • Maximum audio speed-up rate: Maximum audio speed-up rate. Default: 100.

  • Maximum video slow-down rate: Maximum video slow-down rate. Default: 10 (cannot exceed 10).

  • Number of characters per line for CJK: Number of characters per line for Chinese, Japanese, and Korean subtitles; more than this will resu lt in a line break

  • Number of words per line for Other: Number of words per line for subtitles in other languages; more than this will result in a line break

【Whisper Prompt】 ​

  • initial prompt for Simplified Chinese: Initial prompt for the Whisper model for Simplified Chinese speech.

  • initial prompt for Traditional Chinese: Initial prompt for the Whisper model for Traditional Chinese speech.

  • initial prompt for English: Initial prompt for the Whisper model for English speech.

  • initial prompt for French: Initial prompt for the Whisper model for French speech.

  • initial prompt for German: Initial prompt for the Whisper model for German speech.

  • initial prompt for Japanese: Initial prompt for the Whisper model for Japanese speech.

  • initial prompt for Korean: Initial prompt for the Whisper model for Korean speech.

  • initial prompt for Khmer: Initial prompt for the Whisper model for Khmer speech.

  • initial prompt for Russian: Initial prompt for the Whisper model for Russian speech.

  • initial prompt for Spanish: Initial prompt for the Whisper model for Spanish speech.

  • initial prompt for Thai: Initial prompt for the Whisper model for Thai speech.

  • initial prompt for Italian: Initial prompt for the Whisper model for Italian speech.

  • initial prompt for Portuguese: Initial prompt for the Whisper model for Portuguese speech.

  • initial prompt for Vietnamese: Initial prompt for the Whisper model for Vietnamese speech.

  • initial prompt for Arabic: Initial prompt for the Whisper model for Arabic speech.

  • initial prompt for Turkish: Initial prompt for the Whisper model for Turkish speech.

  • initial prompt for Hindi: Initial prompt for the Whisper model for Hindi speech.

  • initial prompt for Hungarian: Initial prompt for the Whisper model for Hungarian speech.

  • initial prompt for Ukrainian: Initial prompt for the Whisper model for Ukrainian speech.

  • initial prompt for Indonesian: Initial prompt for the Whisper model for Indonesian speech.

  • initial prompt for Malay: Initial prompt for the Whisper model for Malaysian speech.

  • initial prompt for Kazakh: Initial prompt for the Whisper model for Kazakh speech.

  • initial prompt for Czech: Initial prompt for the Whisper model for Czech speech.

  • initial prompt for Polish: Initial prompt for the Whisper model for Polish speech.

  • initial prompt for Dutch: Initial prompt for the Whisper model for Dutch speech.

  • initial prompt for Swedish: Initial prompt for the Whisper model for Swedish speech.

  • initial prompt for Hebrew: Initial prompt for the Whisper model for Hebrew speech.

  • initial prompt for Bengali: Initial prompt for the Whisper model for Bengali speech.

  • initial prompt for Persian: Initial prompt for the Whisper model for Persian speech.

  • initial prompt for Urdu: Initial prompt for the Whisper model for Urdu speech.

  • initial prompt for Cantonese: Initial prompt for the Whisper model for Cantonese speech.

  • initial prompt for Norwegian: Initial prompt for the Whisper model for Norwegian speech.

  • initial prompt for Romanian: Initial prompt for the Whisper model for Romanian speech.

  • initial prompt for Greek: Initial prompt for the Whisper model for Greek speech.

  • initial prompt for Filipino: Initial prompt for the Whisper model for Filipino speech.