-
复现流程：
1. git clone https://github.com/PaddlePaddle/PaddleSpeech.git
2. 修改 PaddleSpeech/paddlespeech/s2t/exps/deepspeech2/model.py 函数 setup_model(self)(在末尾部分)为
```
def setup_model(self):
…
-
Research and verify the possibility of training a DeepSeach model for Brazilian Portuguese.
Related docs:
- https://deepspeech.readthedocs.io/en/r0.9/TRAINING.html
- https://commonvoice.mozilla.o…
-
# 简述
本文以 DeepSpeech2 为例说明如何在 Paddle 3.0 下，导出 PIR格式 的新静态图。虽然本文主要关注如何进行导出PIR，但验证 Example 文件夹下的脚本的流程与遇到的问题基本与本文类似，可以在测试前，先阅读本Issue。
本文的主要说明内容如下
- 如何将 DeepSpeech2 运行测试、导出、验证导出的流程
- 问题说明1：Example中存在说…
-
Traceback (most recent call last):
File "/content/SyncTalk/data_utils/deepspeech_features/extract_ds_features.py", line 131, in
main()
File "/content/SyncTalk/data_utils/deepspeech_feature…
-
我的python版本为3.7，安装的paddlepaddle版本为paddlepaddle-rocm 0.0.0，该paddlepaddle版本适配于我的超算平台，能够使用加速卡进行加速，已完成对WenetSpeech数据集的标注和训练数据集的制作，到最后一步训练模型时运行命令：CUDA_VISIBLE_DEVICES=0,1,2,3 python train.py，报下面的错误：
W111…
-
The use of remote speech-to-text services has some problems:
* privacy
* unavailability of the service
* need of Facebook or other free or paid accounts
* limitations of the number of requests
* …
-
I want to run deepspeech.tflite on NPU and need to get deepspeech-0.9.3-models.tflite in int8 or int16 format. How can I use existing deepspeech-0.9.3-models.tflite float32 type to get an int type?
-
hi,can you help me?thanks
orangepi@orangepi5 [c] (DeepSpeed) 3.6.15 ~/ar master ● git clone https://github.com/mozilla/DeepSpeech.git
Cloning into 'DeepSpeech'...
remote: Enumerating ob…
-
Audio features are extracted from a pretrained DeepSpeech model. However, this step is too slow. The 5 seconds wav file need to speed 10 seconds for extracting npy file.
Are there some methods can…
-
### Description of the bug:
[`rules_git`](https://gitlab.arm.com/bazel/rules_git), when checking out the working directory into a `declare_directory` will occasionally report:
```
ERROR: github-…