-
Notifications
You must be signed in to change notification settings - Fork 90
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
用CTC直接微调效果非常差 #39
Comments
hugging face使用我用的是Wav2Vec2Model,没有用Wav2Vec2ForCTC,不知道是不是因为这个。另外,common voice是多语言吧,我们的模型只在中文上训练的。其他语言能力未知 |
common voice的中文数据,2GB的那个,Facebook那个也是没有CTC,自己做词表,然后接CTC微调 |
@zyh3826 你直接CTC微调最后成功了吗 |
没有,换fb的模型了 |
你好,我想请教一下怎么自己做词汇表?? |
时间有点久了,忘记怎么操作的了 |
遇到了一样的问题,loss下降到一定值以后就不再下降,输出全是空白 |
在common voice上使用huggingface的
Wav2Vec2ForCTC
进行微调,模型加载loss从160直接干到4就不降了,预测的时候输入一句话,其输出向量每一行都是一样的,也就是说只输出同一个字,如图





train loss
eval loss
logits
pred_id
怎么调都无法成功。
但是在common voice上用
facebook/wav2vec2-large-xlsr-53
微调是有效果的The text was updated successfully, but these errors were encountered: