-
https://practicaldatascience.co.uk/machine-learning/how-to-transcode-youtube-videos-with-openai-whisper
-
https://apps.microsoft.com/detail/9n0ln23qmx33?hl=zh-cn&gl=CN
能够解决whisper断句混乱的问题,前提是输出的字幕有标点符号,应该什么语言都行。用chatgpt生成三、四句和视频相对应的台词,比如游戏直播,我就以游戏主播的口吻生成几句带标点的话(和视频同语言),然后复制到“初始提示词”中,如果你是0.8.0版本,还需要复制到“热…
-
Is there a parameter I can set to enable more verbose inference? Stuff like segment-level printing and execution times for functions would help a ton.
-
Videos on YouTube can optionally be published under a CC-BY license. We can identify these videos with the YouTube API, download them, and transcribe them with an ASR system like [whisperX](https://gi…
-
I noticed that passing on the language to WhisperX does not work if that language is not in the accepted list of WhisperX. However WhisperX does support loading your own model with specifying the Wav2…
-
time whisperx kJ--A1UyQfg.mp4 --model=large-v3 --align_model WAV2VEC2_ASR_LARGE_LV60K_960H --compute_type int8 --language en --output_format json
```
Lightning automatically upgraded your loaded…
-
It there any plan to add feature of [diarization](https://github.com/pyannote/pyannote-audio)? Thanks for the great work!
-
I've been using whisper with my AMD 6600 XT, which functioned well with ROCM support. However, with whisperx, it seems like it is not supported to use AMD GPUs. Is there any chance for ROCM support to…
-
Command I input to windows powershell:
`subsai .\file --model m-bain/whisperX --model-configs '{\"model_type\": \"large-v2\", \"device\": \"cuda\"}' --format srt `
And result is:
`TypeEr…
-
An option to choose the voice for each person detected with whisperx to keep people in a video
b4zz4 updated
5 months ago