Batuhan Diler

Import Error while using dbnet18

1

Basically I tried to initialize reader with this line, `self.reader = easyocr.Reader(['en'], gpu=True, detect_network = 'dbnet18')` `ImportError: /home/batuhandiler/.local/lib/python3.8/site-packages/easyocr/DBNet/assets/ops/dcn/deform_conv_cuda.cpython-38-x86_64-linux-gnu.so: undefined symbol: _ZNK3c1010TensorImpl36is_contiguous_nondefault_policy_implENS_12MemoryFormatE` My torch version is 1.12 with related torchvision. Cuda...

Hi everyone, Easy OCR really makes great job with GPU but it takes too much video ram. I want to reduce GPU usage. How can I do it ? I...

Hi everyone! craft_mlt_25k.pth uses 3 GB of video ram. I think this is overkill for my work. Do you have any lightweight CRAFT network ? Thank you! Batu.

HIgh Memory Usage

3

Hi, Thanks for this great repository. It is amazing work. My problem is when I initialize OpenVoice's BaseSpeakerTTS, It uses ~3 GiB memory and ~1 GiB video ram. I think...

What do you think about adding German ?

6

Hey, Thanks for this great repository. Do you guys think to add German ?

How can I check segments are empty or not ?

1

Hi everyone, I need to check detected segments empty or not. In order to achieve that I have tried this, ``` segments, info = self.whisper_model.transcribe(audio_data, **self.options.transcribe_settings) try: next(segments) except StopIteration:...

Cannot install CUDA 12.1

4

Hi All, I want to install CUDA12.1 with my containers but it only installs cuda 11.4 each time when I write cuda:12.2 jetson-containers build --build-flags=--no-cache --name=cu122 cuda:12.2 EDIT: Now I...