-
Hi @kpu , I met a weird issue: training the n-gram model with relative small corpus was OK, but it raised baddiscount error with even more corpus
1. Training the N-gram model with corpus of 20 mill…
-
#### What is your question?
I am trying to replicate the results for the new wav2vec-u (https://ai.facebook.com/research/publications/unsupervised-speech-recognition) model (currently working on TIMI…
-
We need to figure out if any work and/or research has been done on automatically detecting and correcting Bangla spelling mistakes. Technically speaking, are there papers, notebooks, or packages that …
-
```
What steps will reproduce the problem?
1. Compile trunk (r48)
2. Download an arpa LM e.g. the LM in
http://www.keithv.com/software/giga/lm_giga_64k_nvp_3gram.zip
3. Run evaluate-ngram which load…
-
-
I created (unofficial) PKGBUILD files for Arch Linux, which can be downloaded here:
[https://github.com/stes/arch-deepspeech](https://github.com/stes/arch-deepspeech)
If desired to include such …
-
'gbk' codec can't decode byte 0x8c in position 2088: illegal multibyte sequence
File "[C:\Users\Administrator\.paddlehub\modules\fastspeech2_baker\module.py]()", line 73, in __init__
self.fron…
QL-AR updated
8 months ago
-
## 🐛 Bug
This is a workaround of the [issue closed as expected behavior](https://github.com/pytorch/pytorch/issues/49260), but there are a similar error without pickling.
## To Reproduce
Code…
-
pip install pycorrector后运行报错：
>>> from pycorrector import Corrector
>>> m = Corrector()
>>> m.correct('你好')
Traceback (most recent call last):
File "/home/izhaowo/.local/lib/python3.9/site-pa…
-
One might have two language models for example, one with just commands, and one for general English text. The first is used to detect voice commands, and the second to understand a parameter to a comm…