-
I am looking for a simple procedure to generate FST (finite state transducer) from cmudict-0.7b or cmudict-0.7b.dict, which will be used with phonetisaurus.
I tried following set of commands (phoneti…
-
In the pretrained Transducer model, the greedy decoding strategy has a max_symbols_per_step parameter equal to 5. I was wondering why is it not "None" and shouldn't the transducer perform better witho…
-
Currently, Redux Toolkit adds thunks as the default supported approach for any kind of async / side effect behavior, largely because it's the simplest possible approach that works, and because it's al…
-
we can optimize fuzzyquery by using AutomatonTermsEnum. The idea is to speed up the core FuzzyQuery in similar fashion to Wildcard and Regex speedups, maintaining all backwards compatibility.
The adv…
-
Search mode is the error detection stage of analiticcl, where running text is passed as input, and analiticcl attempts to identify and correct parts of the text that require correction, regardless of …
-
Hey rhvoice devs and contributors. Can you tell me how I can make a dictionary for arabic, knwing that I'm not a developer? Does it require c++ programming? Can you site me to the documentation on how…
-
I read the book and is pretty interested. Is there any future reading I should take a look into?
-
你好，
请教一下关于命令词识别流程的一点疑问：
1：MultiNet似乎是参考的CRNN，但是我从CRNN原文中未找到关于音素（phoneme）的相关说明，想问一下，这里的音素是啥，能够举个例子；
2：语言模型是有什么作用，能够也举个例子。
谢谢
-
Hi,
I facing some trouble while expanding acronyms. Let's say I have the following code:
```python
# sigma_star is: a-zA-Z0-9 + punctuation
_lambda = pynini.string_map([("AE", "a e"), ("AEB", "a…
-
## About
The existing error handling logic in thi.ng/rstream has been somewhat _peculiar_ (to say the least) and has been source of various confusions and unexpected outcomes. The #279 PR is aiming…