-
anyone is there Who working on TensorRT whisper on multinugal?
i do try multiple on smal/medium/large-v3 model.
but all model is printing on english output.
please help me~!!!@
**serve…
-
Hello,
I'd like to transcribe multiple different audios in a batched manner, with varying context lengths. The official example is not reflective of this, as it just [repeats](https://github.com/NV…
-
**info**
- env : google colab
- os : ubuntu jammy x86_64
- python : 3.10.12
**steps**
```
pip install -U whisperx
!wget -c https://raw.githubusercontent.com/marl/pysox/master/tests/data/input…
-
### 🐛 Describe the bug
`torch.onnx.export` in Pytorch 1.13 introduces additional bias inputs to conv layers which causes NVIDIA TensorRT conversion to fail with the following error:
```
Errors o…
-
Hi, should TensorRT (docker) or FasterWhisper be used on a Windows 4080/4090 laptop and what are the advantages/disadvantages of each?
-
If I install your pinned version of tensorrt (0.8.0.dev2024012301 - from your 'install_tensorrt.sh' file), then I get an undefined symbol when I load the model
`model = whisper_s2t.load_model(model…
-
Not sure how to supply a list of prompts corresponding to a list of filenames. If I pass in two different audio files to transcribe, with `initial_prompts=None` it works. If I pass `initial_prompts=["…
-
### System Info
- Architecture: x86_64
- CPU: AMD Ryzen Threadripper 1920X 12-Core Processor
- NVIDIA RTX 3090
- Driver Version: 545.29.06
- Container Tag: cuda12.1-devel-ubuntu22.04
### Who…
-
Is conversion to whisper large-v2 currently supported?
-
Good day everyone.
I’ve been trying to get the latest version of Whisper AI running to no avail.
So I follow the instructions and get a Restart Session pop up and wait for the thing to install an…
MHA11 updated
6 months ago