-
Hi, @Huishou TIMIT is a speech dataset aligned with its phonemes, the net1 is a speech recognizer trained with the speech and the phoenemes equivalent, then pass the recognized from net1 to net2, net2…
-
firsr, thank you for your excellent work.
And I have a question about how to use phonemes to train models? not in other works, only in this tacotron2.
-
Hello, thank you for amazing work! Couldn't understand how to translate English text (on which I want to inference your model) to torch tensor of tokens IDs. As far as I understand you firstly convert…
-
The Arabic support as written needs improving. Specifically:
- [ ] Use more standard Arabic phoneme names (https://en.wikipedia.org/wiki/Arabic_phonology), e.g. `a:` instead of `aa` (it seems done …
-
For support and discussions, please use our [Discourse forums](https://discourse.mozilla.org/c/deep-speech).
If you've found a bug, or have a feature request, then please create an issue with the f…
-
Hi there, and thanks for the great app.
I always find the female voices better for navigation, as they can be heard over the traffic noises, but there isn't a Scottish or British female one, only a…
-
如题,请问微调训练需要多少数据量呢?文档里只给了 conversion的数据量情况:10条,3分钟。微调训练也是这样吗?
另外汉语cleaner也看不太懂,没有看到拼音声调怎么处理的。请问mandarin.py里边的各种音素符号映射知识,是参考的哪个项目?另外为什么不用统一的某一种phoneme表示,而是先bopomofo,再转罗马拼音,再转IPA,这么转来转去的作用是什么?
-
Dear contributors,
Thank you for sharing your great works.
I have successfully reproduced your result with the LJSpeech Dataset.
In addition, I have trained your model with Korean Single Spea…
-
Hi,
I would like to use the pretrained acoustic model for English but use it in combination with a new in-domain language model, for which I have to generate pronunciations.
I am used to the Kal…
-
`model('今天来的目的是什么?')
model = G2pM()
model('今天来的目的是什么?')
output:['jin1', 'tian1', 'lai2', 'de5', 'mu4', 'de5', 'shi4', 'shen2', 'me5', '?']`
是否是安装问题。
g2pm 版本为0.1.2.4