parrots

parrots copied to clipboard

>>> import parrots >>> text = parrots.speech_recognition_from_file('./16k.wav') Traceback (most recent call last): File "", line 1, in AttributeError: module 'parrots' has no attribute 'speech_recognition_from_file' How to solve this problem? Thanks.

Mr-Biang

安装时 keras 导入包报错

1

ImportError: cannot import name 'Adam' from 'keras.optimizers'

nuck555

1. Add tf 2.6 support 2. fix pinyin_hanzi_dict path

yun-li

配合 tensorflow==1.13.1 需要使用的keras版本号是？

beiliubei

Architectural description of parrots and how to train in english or any other language

1

alokprasad

无法下载

4

- [ ] I checked to make sure that this is not a duplicate issue ### Describe the solution you'd like A clear and concise description of what you want...

BlackTravel

大佬您好，关于显存释放问题

1

大佬您好，执行完m.predict(）推理以后，显存是不会立马释放掉，请问如何可以释放掉显存占用。

ganjunhong

parrots pip安装后，使用命令打开一直卡住

2

 运行web 页面也是卡着不动 

lonngxiang

下载问题

1

rying to resume download... pytorch_model.bin: 19%|██████████ | 126M/651M [01:30

20246688

关于直接使用默认模型生成效果问题

3

### Describe the Question Please provide a clear and concise description of what the question is. 群主您好，我用单独再训练的模型放进去，效果跟gpt-sovits的那个基本是一样的，效果也非常好。 但有个问题是，我在测试gpt-sovits这个默认模型的时候，gpt-sovits的效果很好， 但是在parrots引入用gpt-sovits的默认模型，效果却不一样，不知道是否是代码还需要在哪里完善呢？ sovits_model_path 和gpt_model_path都是默认模型地址 m = TextToSpeech( bert_model_path = pwd_path+"/models/gpts_pretrained_models/chinese-roberta-wwm-ext-large", hubert_model_path = pwd_path+"/models/gpts_pretrained_models/chinese-hubert-base",...

ganjunhong