-
When running Lab 3 commands from the readme that use ctc loss, this error it thrown
```fsdl-text-recognizer-2021-labs/lab3/text_recognizer/lit_models/base.py", line 24, in update
preds = torch…
-
@piiswrong, @szha: Now that cuDNN 7 supports CTC loss, perhaps we should discard the current GPU implementation in contrib.ctc_loss (adapted from the WarpCTC implementation) and only use cuDNN for GPU…
-
Not able to get individual confidence score while doing using CTC but able to get it using 'Attn'(test.py). How to get individual confidence score for a Text example 'Coming' using CTC. Thanks in adva…
-
Hi. Does anyone know how to extract the confidence score of the prediction in a model trained with the 'CTC' module?
I only found the example with 'Attn' in this repo:
```
confidence_score_list …
-
(base) [jianming_ge@localhost build]$ make ..
(base) [jianming_ge@localhost build]$ cmake ..
-- cuda found TRUE
-- Building shared library with GPU support
-- Configuring done
-- Generating done
…
-
after enter `mingw32-make `, got following:
```
[ 1%] Building CXX object CMakeFiles/asr_test.dir/src/am/am.cpp.obj
[ 3%] Building CXX object CMakeFiles/asr_test.dir/src/asr/asr.cpp.obj
[ 5%]…
-
在common voice上使用huggingface的`Wav2Vec2ForCTC`进行微调，模型加载
```python
model = Wav2Vec2ForCTC.from_pretrained(
model_path,
…
-
**Checklist:**
- [X] I updated to the latest version available
- [X] I cleared the cache of my browser
**Release with the issue:** 1.3.6 / Home Assistant 2024.7.4
**Last working release…
-
Anytime I try to train the CTC model it comes back with a value error
`ValueError: Cannot evaluate tensor using `eval()`: No default session is registered.`
Tried setting a default session with…
-
TensorFlow r0.8 has added the implementation of CTC loss, will tflearn support CTC loss?