PaddleSpeech icon indicating copy to clipboard operation
PaddleSpeech copied to clipboard

Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translation a...

Results 322 PaddleSpeech issues
Sort by recently updated
recently updated
newest added

请问输入一段音频在encoder outputs,中返会的维度是[1 T, D],这个T要怎么和音频的长度对应上呢?

Question
Stale

您好,我在ted_en_zh这个st任务中尝试切换数据集。 1.之前切换过相对小的数据集(6000句左右),能够运行并验证,但是验证的时候,对于读取的任何wav,hyp一直只重复同一句结果,请问什么原因呢?修改了epoch但是没有效果。 2.这次切换了一个只有400条的极小数据集(因为文本更准确),在第一步数据处理部分就出现了这个问题,请问如何修改? ` 2022-06-03 20:13:34.284 | INFO | paddlespeech.s2t.frontend.augmentor.augmentation:__init__:123 - Augmentation: [] Traceback (most recent call last): File "/home/aistudio/work/PaddleSpeech/utils/compute_mean_std.py", line 87, in main() File "/home/aistudio/work/PaddleSpeech/utils/compute_mean_std.py", line 82, in main...

Question
Stale

在`punc_restore.py'73行后中加入 ```python static_model = jit.to_static( model, input_spec=[ InputSpec([-1], dtype=paddle.int64), InputSpec([-1], dtype=paddle.int64), ], ) logits, _ = static_model(input_ids, seg_ids) ``` 报错: ``` paddlespeech/text/exps/ernie_linear/punc_restore.py", line 84, in test logits, _ = static_model(input_ids,...

**Describe the bug** 在运行paddlespeech/s2t/exps/u2/bin/export.py脚本将Transformer模型转换成inference格式时出错。 **Screenshots** ** Environment (please complete the following information):** - OS: macOS 12.2.1 - Python Version 3.9.11 - PaddlePaddle Version 2.2.2 - PaddleSpeech Version r0.1.1 **Additional context**...

我想根据自己的使用场景,增加数据再训练一下流式语音识别,请问要训练example下面的哪个文件呢?

Question
Stale

Conformer/Transformer 支持 amp

Stale
conflicts
S2T
Test

识别长语音时发生报错,说要少于50秒,能否支持长时间的音频? ------------------------------ [2022-06-08 14:38:19,952] [ INFO] - checking the audio file format...... [2022-06-08 14:38:19,956] [ ERROR] - Please input audio file less then 50 seconds.

FAQ
S2T

This issue needs to be solved at the same time as https://github.com/PaddlePaddle/PaddleSpeech/issues/1282 see: [DurIAN](https://arxiv.org/abs/1909.01700)

feature request
T2S

- [ ] mem pool - [x] wfst decoder - [ ] timeline decoder - [x] fbank & mfcc - [x] get partial result - [x] websoket server - [x]...

Stale
Deployment

![bcfae547bf3622ba43a544ec4ae3d1f](https://user-images.githubusercontent.com/108966996/191884046-72dbf042-029d-4f75-846e-4757b7ee3fa1.jpg) ![微信图片_20220923105440](https://user-images.githubusercontent.com/108966996/191884103-6d6cde41-b410-49ae-8c99-d52657e6fe6f.jpg) 为什么运行了setup.py之后还是没有相关的库呀

Question