transformer

Feature request

We currently have 2 monocular depth estimation models in the library, namely DPT and GLPN.

It would be great to have a pipeline for this task, with the following API:

from transformers import pipeline

pipe = pipeline("depth-estimation")
pipe("ca

Is there a way to train a bidirectional RNN (like LSTM or GRU) on trax nowadays?

https://github.com/PaddlePaddle/PaddleNLP/tree/develop/examples/machine_translation/transformer
在我们的基于 Transformer 的 Machine Translation 例子中，数据准备这一步奏仅提供了一个预处理好的 WMT14 en-de 数据，并没有告诉读者该怎么处理数据，每一步应该怎么做，可否像 fairseq (https://github.com/facebookresearch/fairseq/tree/main/examples/translation) 一样，将每一个步奏都提供出来。

另外，我们的PaddleNLP数据处理看起来和代码高度耦合。意思就是我每想用新的机器翻译数据训练模型，我需要在PaddleNLP里先写一些支持该数据的新的代码。这从用户的视角看并不是

From paper, it mentioned

Instead, the training data generator chooses 15% of tokens at random, e.g., in the sentence my
dog is hairy it chooses hairy.

It means that 15% of token will be choose for sure.

From https://github.com/codertimo/BERT-pytorch/blob/master/bert_pytorch/dataset/dataset.py#L68,
for every single token, it has 15% of chance that go though the followup procedure.

Please report TTS text frontend bugs here, for examples: text normalization, polyphone and tone sandhi, etc.

We encourage developers to solve these problems.

1. polyphone: 能说多长(zhang3 ❎)的语音呢？是否可以长(zhang3 ❎)语音合成呢？长(chang2 ✅)语音，长(zhang3 ❎)文本

We keep this issue open to collect feature requests from users and hear your voice. Our monthly release plan is also available here.

You can either:

1. Suggest a new feature by leaving a comment.
2. Vote for a feature request with 👍 or be against with 👎. (Remember that developers are busy and cannot respond to all feature requests, so vote for your most favorable one!)
3. Tell us that you wo