-
Dataloader name: `asr_sindodusc/asr_sindodusc.py`
DataCatalogue: http://seacrowd.github.io/seacrowd-catalogue/card.html?asr_sindodusc
| Dataset| asr_sindodusc |
|-------------|---|
| Description …
-
Use this issue to discuss the [gender or sex pattern in the GOV.UK Design System](https://design-system.service.gov.uk/patterns/gender-or-sex/).
## What
When and how to ask about people's gender a…
-
A Step-By-Step Guide to Name Your Product
https://ift.tt/3fjwcdB
About 0 Minutes
Quick. Look at these images. Which is kiki? And which is bouba?
Did you attribute kiki to the pointy shape? And b…
-
Hi,
Speaker recognition during diarization seems rather deficient in some cases. A few examples below.
Do you believe that segmenting first, then diarizing each track independently and then tryi…
mirix updated
9 months ago
-
Dataloader name: `asr_smaldusc/asr_smaldusc.py`
DataCatalogue: http://seacrowd.github.io/seacrowd-catalogue/card.html?asr_smaldusc
| Dataset| asr_smaldusc |
|-------------|---|
| Description | Th…
-
## Issue
I discreetly followed the tutorials (such as [this](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.3/doc/doc_ch/recognition.md)) and fine-tuned on arabic_PP-OCRv3_rec model [here](…
-
current method:
1. Run compile script
2. script downloads firmware
3. extracts firmware
4. replace kernel
5. repack firmware
6. flash demo.bin
7. boot wz_mini
The downside to this, is the …
-
Hi! I tried the speaker identification using the python code and it works great! Am wondering if it can be modified to output the match scores as well or the highest score. This can help with debuggin…
-
**Describe the bug**
I trying to use Python Cognitive Service Speech SDK on Armbian ubuntu on [OrangePi4 LTS](http://www.orangepi.org/orangepiwiki/index.php/Orange_Pi_4_LTS).
This is a bare-metal U…
-
Batch size is 2048. Getting the training data from the q I see
x_train, y_train = train_q.get()
print('X.. ' + str(x_train.shape) + ' Y.. ' + str(y_train.shape))
X.. (2048, 2980) Y.…