-
This Diarization code was working fine in the morning.
Code -
```
import whisperx
import gc
device = "cuda"
audio_file = "audio.mp3"
batch_size = 16 # reduce if low on GPU mem
compute_ty…
-
我做过相关AI字幕的工作，不方便上传代码，但有几个方向值得借鉴：
- 不用whisper，用whisperX，然后用whisper原始输出的字幕作为原本，扫描出准确时间轴
- 用更智能的方式切割映像文件，只检测出里面有语音的部分，并采用不同的设置喂给whisperX
- 将不同的whisper和wav2vec2模型的结果进行一个综合导出
最后时间轴的结果里无需人为修正的准确结果可以…
-
Hello WhisperX Team,
I appreciate the great work you've done on WhisperX! I've noticed that the speaker diarization feature requires a HuggingFace token, which introduces a dependency on an externa…
-
I tried to follow the instruction for use the whisperX in my python code but I have compatibility issues during the dependency installation.
I'm creating a python env with:
`python3.10 -m venv ven…
-
I am doing some dataset collection for voice cloning work and as I understand it, (and correct me if I'm wrong) numbers in the transcript should be transcribed as words rather than the digits whisperx…
-
Obviously, you already changed the script to get rid of the bug. But now, I still get an error at step 6. It now says that the variable "result_merged" is not defined:
```
NameError …
-
Thanks for the great work here m-bain and contributors.
I have previous versions successfully running, but cannot get the latest version to run.
I am experiencing the error: **`'SpeakerDiarization' …
-
项目跑起来后，访问http://localhost:8501/，报错，如下
`ModuleNotFoundError: No module named 'whisperx'
Traceback:
File "/opt/homebrew/anaconda3/lib/python3.12/site-packages/streamlit/runtime/scriptrunner/exec_co…
-
After download the [model.bin] I get following error:
> tts_models/multilingual/multi-dataset/xtts_v2 is already downloaded.
> Using model: xtts
model.bin: 100%|█████████████████████████████████…
-
I noticed that it would fallback to English if no language is specified. Is there a way to automatically predict the language?