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 289 PaddleSpeech issues
Sort by recently updated
recently updated
newest added

ImportError: /lib/x86_64-linux-gnu/libc.so.6: version `GLIBC_2.32' not found 目前解决方案是opencc降级 pip install opencc-python-reimplemented==0.1.6 但是你一旦想着要升级glibc,就是无尽的麻烦 希望能直接固定opencc版本,避免后面更多人遇到这个问题

feature request

环境:windows10 CPU Core i7 ``` conda create -n audio python=3.9 libuv conda activate audio pip install paddlepaddle -i https://mirror.baidu.com/pypi/simple pip install pytest-runner paddlespeech==1.4.1 或者 paddlespeech==1.4.0 pip install langid==1.1.6 zhconv==1.4.3 transformers==4.31.0...

Bug
T2S

Mac M2 上 安装了 paddlepaddle 2.4.2, paddlespeech 2.4.1。 跑官方的第一个示例(语音转文本)时,报错提示paddlespeech_ctcdecoders 找不到,没有安装 下面是错误信息: python3 ./src/pp.py /Users/ccc/.pyenv/versions/3.8.18/lib/python3.8/site-packages/librosa/core/constantq.py:1059: DeprecationWarning: `np.complex` is a deprecated alias for the builtin `complex`. To silence this warning, use `complex`...

Question

## General Question 我以前用的时候还是正常的,最近都是这样了。比如「关关雎鸠,在河之洲」,最后那个“鸠”一定还没读完就结束了。其他句子也是同理,句号、感叹号,都有这种情况。不知道你们有没有发现。 我的参数设置: ```python wav_file = tts_executor( text=txt_contents, am='fastspeech2_canton', voc='hifigan_csmsc', lang='canton', spk_id=10, use_onnx=True, output='api_1.wav', cpu_threads=0 ) ```

Question

Maybe we can make her British Accent for training https://www.youtube.com/@EnglishwithLucy

Question

speech_web中,跑小数据微调完成后,后台显示运行结果为0,证明微调成功,但是页面还是显示微调中。然后输入在试验路径中输入微调后的路径,点击合成后,后台报错 /home/deepiot/anaconda3/envs/paddle2.4/lib/python3.8/site-packages/_distutils_hack/__init__.py:33: UserWarning: Setuptools is replacing distutils. warnings.warn("Setuptools is replacing distutils.") Traceback (most recent call last): File "/home/deepiot/ai/PaddleSpeech-develop/paddlespeech/t2s/exps/fastspeech2/../synthesize_e2e.py", line 27, in from paddlespeech.t2s.exps.syn_utils import get_sentences_svs ImportError: cannot import name 'get_sentences_svs'...

Bug
T2S

环境: ubuntu20.04 cuda 12.0 cudatookit 8.9 paddlepaddle-gpu==2.5.2.post120 ![微信图片_20240121151605](https://github.com/PaddlePaddle/PaddleSpeech/assets/36878412/d9cfd3a3-63cc-4352-b90e-7c16f13ebaaf) `File "/hone/intel/.conda/envs/speech10/lib/python3.10/site-packages/paddlespeech/cl1/asr/infer ,py", line 303, in inferresult transcripts = self.model.decode(File "/home/intel/.conda/envs/speech10/lib/python3.10/site-packages/decorator.py", line 232, in funreturn caller(func.*(extras +args)File "/home/intel/.conda/envs/speech10/lib/python3.10/site-packages/paddle/fluid/dygraph/base.py", line 347, in _decorate...

Bug
T2S

有比较明确的能跑起 demo 的安装环境的详细步骤或推荐的步骤嘛,搞了二天了没搞定。。。不是依赖报错,就是运行时有问题。。。 目前运行官方的 Automatic Speech Recognition 示例后,报这个错。 2024-01-22 19:21:14.135 | INFO | paddlespeech.s2t.modules.embedding:__init__:153 - max len: 5000 [1] 76255 segmentation fault python3 ./src/pp.py /Users/.pyenv/versions/3.10.13/lib/python3.10/multiprocessing/resource_tracker.py:224: UserWarning: resource_tracker: There appear to...

Question