Inference error size:mismatch

ming024 / FastSpeech2

An implementation of Microsoft's "FastSpeech 2: Fast and High-Quality End-to-End Text to Speech"

MIT License

1.79k stars 530 forks source link

Inference error size:mismatch #127

Closed yanzhuangzhuang-beep closed 2 years ago

yanzhuangzhuang-beep commented 2 years ago

when i use the config "python synthesize.py --text "大家好，欢迎收听我的频道" --speaker_id 0 --restore_step 100000 --m ode single -p config/AISHELL3/preprocess.yaml -m config/AISHELL3/model.yaml -t config/AISHELL3/train.yaml" Then show a problem

size mismatch for speaker_emb.weight: copying a param with shape torch.Size([218, 256]) from checkpoint, the shape in current model is torc h.Size([1, 256]).

zaynabmu commented 2 years ago

@yanzhuangzhuang-beep Hi how did you solve this problem ? I faced it currently

thank you in advance