The numbers in the text of English to speech conversion have always been in Chinese pronunciation

[JUN-ZZ]

Self Checks

• I have thoroughly reviewed the project documentation (installation, training, inference) but couldn't find any relevant information that meets my needs. English 中文 日本語 Portuguese (Brazil)
• I have searched for existing issues search for existing issues, including closed ones.
• I confirm that I am using English to submit this report (我已阅读并同意 Language Policy).
• [FOR CHINESE USERS] 请务必使用英文提交 Issue，否则会被关闭。谢谢！:）
• Please do not modify this template :) and fill in all the required fields.

1. Is this request related to a challenge you're experiencing? Tell us your story.

The numbers in the text of English to speech conversion have always been in Chinese pronunciation

2. What is your suggested solution?

The numbers in the text of English to speech conversion have always been in Chinese pronunciation

3. Additional context or comments

The numbers in the text of English to speech conversion have always been in Chinese pronunciation

4. Can you help us with this feature?

• I am interested in contributing to this feature.

[PoTaTo-Mika]

Any examples?

[mashdragon]

Example ( see #716 too)

1. Run the api_client with text "1, 2, 3. One hundred one. 101. One thousand eighty-four. 1,084."
2. Review generated audio.

Github does not let me upload audio but here is an example compressed in a zip file:
tts_numbers_fail.zip

Note the issue with number pronunciations is also there when there is lots of English text before the numbers begin

[PoTaTo-Mika]

We suggest you to use words instead of arabic numbers.

[Haoran1272]

use "normalize": false in your api params

[mashdragon]

use "normalize": false in your api params

What does "normalize": false do?

[github-actions]

This issue is stale because it has been open for 30 days with no activity.

[PoTaTo-Mika]

use "normalize": false in your api params

What does "normalize": false do?

convert arabic numbers into chinese words.