Skip to content

[Docathon][Fix Doc Format No.43] Fix rendering of doc rnnt_loss_cn #7568

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Oct 20, 2025
Merged

[Docathon][Fix Doc Format No.43] Fix rendering of doc rnnt_loss_cn #7568

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions docs/api/paddle/nn/functional/rnnt_loss_cn.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@ rnnt_loss

.. py:function:: paddle.nn.functional.rnnt_loss(input, label, input_lengths, label_lengths, blank=0, fastemit_lambda=0.001, reduction='mean', name=None)

计算 RNNT loss。该接口的底层调用了第三方 [warp-transducer](https://github.com/b-flo/warp-transducer.git) 的实现。
计算 RNNT loss。该接口的底层调用了第三方 `warp-transducer <https://github.com/b-flo/warp-transducer.git>`_ 的实现。
也可以叫做 softmax with RNNT，因为 warp-transducer 库中插入了 softmax 激活函数来对输入的值进行归一化。

参数
Expand All @@ -16,7 +16,7 @@ rnnt_loss
- **label_lengths** (Tensor) - 每个标签序列的长度，它应该有形状 [batch_size] 和 dtype int64。
- **blank** (int，可选) - RNN-T loss 的空白标签索引，处于半开放区间 [0,B)。数据类型必须为 int32。默认值为 0。
- **fastemit_lambda** (float，默认 0.001) - FastEmit 的正则化参数(https://arxiv.org/pdf/2010.11148.pdf)。
- **reduction** (str，可选) - 表示如何平均损失，候选是 ``'none'``|``'mean'``|``'sum'`` 。如果 ::attr:`reduction` 是 ``'mean'``，输出将是损失的总和并除以 batch_size;如果 :attr:`reduction` 是 ``'sum'``，返回损失的总和;如果 :attr:`reduction` 为 ``'none'``，则不应用 reduction。默认是 ``'mean'``。
- **reduction** (str，可选) - 表示如何平均损失，候选是 ``'none'`` | ``'mean'`` | ``'sum'`` 。如果 :attr:`reduction` 是 ``'mean'``，输出将是损失的总和并除以 batch_size；如果 :attr:`reduction` 是 ``'sum'``，返回损失的总和；如果 :attr:`reduction` 为 ``'none'``，则不应用 reduction。默认是 ``'mean'``。
- **name** (str，可选) - 操作名称，默认为 None。

返回
Expand Down