faster-whisper-GUI

0.8.1——2024.7.29

HASH

• CRC32: DE11F5CC
• MD5: CA6DB2876A74649166B2FFCBA9D9991E
• SHA-1: CCFC485F8FEBFE9C4498939DB1CC4CA82925D10F

0.8.1 改动

• • 升级 faster-whisper 至 1.0.3 版本

    • Silero VAD V5 model

      • 经过反复测试 Silero V5 模型在背景复杂的情况下表现不佳，请按需升级

提示

• 软件需要完全卸载旧版之后安装新版（cache文件夹可不做清理）

• 需要安装 ffmpeg

0.8.1 Changes

• Upgrade faster-whisper to version 1.0.3

  • Silero VAD V5 model

    • After repeated testing, the Silero V5 model does not perform well with complex backgrounds. Please upgrade as needed

tips

• the software needs to install the new version after completely uninstalling the old version (the cache folder can not be cleaned)

• ffmpeg is required to be installed

0.8.0

HASH

• CRC32：13530B56
• MD5：61ED9AF5F712A27DA32EE34A8E88A5A0
• SHA-1：B415E721D6C54D5E835FD5BD4AD870DA985644AC

0.8.0 改动

• 修复没有赞助渠道的 bug #126

• 升级 faster-whisper 到 1.02 版本

  • 添加 distil-large-v3 模型在线模式支持 #130

    • 最新的 Distil-Whisper 模型 distil-large-v3 本质上是为与 OpenAI 顺序算法配合使用而设计的。

  • 支持初始化更多 whisper 模型参数

    • 音频分段设置

      • max_new_tokens: 每个区块生成的新令牌的最大数量。如果未设置，最大值将通过默认的 max_size 设置。

      • chunk_length: 音频段的长度。如果不是 None，它将覆盖 FeatureExtractor 的默认chunk_size。

      • clip_timestamps: 逗号分隔的要处理的剪辑的时间戳列表（以秒为单位）开始,结束,开始,结束......。最后一个结束时间戳默认为文件的结束。如果使用 clip_timestamps，将忽略 VAD 设置。

    • 幻听参数

      • hallucination_silence_threshold: 当 word_timestamps 为 True 时，当检测到可能的幻觉时，跳过长于此阈值（以秒为单位）的静默期。

    • 其他设置

      • hotwords: 为模型提供的热词/提示短语。如果 prefix 不是 None，则无效。 你可以输入提示词，类似于：“the video is about comfyUI”。

    • 常规

      • language_detection_threshold: 如果语言标记的最大概率高于此值，则会检测为该语言。

      • language_detection_segments: 语言检测需要考虑的分段数量。

    • 其他新特性：https://github.com/SYSTRAN/faster-whisper/releases/tag/v1.0.2

• 修复 复制字幕 功能的 bug

• 更新一些 UI 文字

• 停用 转写参数 页面的 保存参数、读取参数 功能

• 起止时间、说话人 列居中显示

• 升级 pytorch 到 2.3.0 , CUDA12

提示

• 软件需要完全卸载旧版之后安装新版（cache文件夹可不做清理）
• 需要安装 ffmpeg
• 使用 V3 模型时，如果频繁出现显存溢出，请尝试更新显卡驱动程序到最新或者回退到上一个稳定版本，当前版本（2024.5.29）测试结果稳定。

0.8.0 Changes

• Fixed bug with no sponsorship channels #126

• Upgrade faster-whisper to version 1.02

  • Add online mode support for the [distil-large-v3](https://huggingface.co/distil-whisper/distil-large-v3-ct2) model #130

    • The latest Distil-Whisper model, distil-large-v3, is intrinsically designed to work with the OpenAI sequential algorithm.

  • Support initializing more whisper model args

    • max_new_tokens: Maximum number of new tokens to generate per-chunk. If not set, the maximum will be set by the default max_length.

    • chunk_length: The length of audio segments. If it is not None, it will overwrite the default chunk_length of the FeatureExtractor.

    • 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_filter will be ignored if clip_timestamps is used.

    • hallucination_silence_threshold: When word_timestamps is True, skip silent periods longer than this threshold (in seconds) when a possible hallucination is detected

    • hotwords: Hotwords/hint phrases to provide the model with. Has no effect if prefix is not None.

    • language_detection_threshold: If the maximum probability of the language tokens is higher than this value, the language is detected.

    • language_detection_segments: Number of segments to consider for the language detection.

  • fixed bug of copy subtitles

  • Update some UI text

  • Disable the functions of saving parameters and reading parameters on the transfer parameter page

  • Start and end times and speaker columns are displayed in the center

  • Upgrade pytorch to 2.3.0 , CUDA12

tips

• the software needs to install the new version after completely uninstalling the old version (the cache folder can not be cleaned)
• ffmpeg is required to be installed
• When using the V3 model, if memory overflows frequently, please try updating the graphics card driver to the latest or fallback to the previous stable version. The test results of the current version (2024.5.29) are stable.

0.7.6

0.7.6 改动

• 修复转写结束后崩溃的 bug #111

• 修复手动添加多个字幕后表格不能关闭的 bug

• Demucs 新增非人声音轨合并输出 #110

  • 新增人声、其他音轨二分输出

• 字幕显示及编辑相关功能更新

  • 字幕编辑：添加批量增减时间戳功能
  • 字幕表格显示：
    • 添加持续时间过短的时间戳背景色提示功能
    • 说话人 在表格中单独显示为一列

Hash

• SHA-1 : 37C8C46BE3D297AD06FA4C887A69E2FB46CB49AB
• MD5 : 09681381F2AF06749BB70030A411DFB6
• CRC32 : D6FA10B2

提示

• 软件需要完全卸载旧版之后安装新版（cache文件夹可不做清理）
• 需要安装 ffmpeg
• 使用 V3 模型时，如果显存溢出，请尝试关闭 单词级时间戳 ，如果仍然溢出，那么请将量化方式更改为 float16 或者 int8

0.7.6 Changes

• Fixed bug that crashed after transcriptions ended #111

• Fixed a bug where manually adding multiple words behind the scenes table cannot be closed

• Demucs adds combined output of non-vocal tracks #110

  • Added dichotomy output of vocals and other audio tracks

• Updated functions related to subtitle display and editing

  • Subtitle editing: Add batch advance and delay timestamp function

  • The subtitle table shows:

    • Add a prompt function for background color of a timestamp with too short duration

    • Speakers are displayed as a separate column in the table

Hash

• SHA-1 : 37C8C46BE3D297AD06FA4C887A69E2FB46CB49AB
• MD5 : 09681381F2AF06749BB70030A411DFB6
• CRC32 : D6FA10B2

tips

• the software needs to install the new version after completely uninstalling the old version (the cache folder can not be cleaned)
• ffmpeg is required to be installed
• When using the V3 model, if the memory of GPU overflows, try turning off the word-level timestamp. If it still overflows, change the quantization method to float16 or int8

0.7.2

0.7.2 改动

• 修正界面翻译不彻底的问题 #106
• 修复添加表格的逻辑 bug
• 修复 whisperX 不能批量处理的 bug
• 精简安装包大小

提示

• 软件需要完全卸载旧版之后安装新版（cache文件夹可不做清理）
• 需要安装 ffmpeg
• 转写结束之后或许存在不稳定的崩溃状况，如果转写结束之后崩溃，请关闭转写完成自动跳转功能，并在转写结束之后稍等片刻再点击跳转到结果页面

0.7.2 Changes

• Fixed the problem of incomplete interface translation #106

• Fix logic bug in adding tables

• Fix WhisperX bug that can't be processed in batches

• Thin Package Size

tips

• the software needs to install the new version after completely uninstalling the old version (the cache folder can not be cleaned)
• ffmpeg is required to be installed
• -there may be an unstable crash condition after the end of processing. if the crash occurs after the transcript ends, please turn off the automatic jump function, and wait a moment after process, and then click to jump to the result page.