Nixon

The program crashes when I use the argument "--load_optimizer"

2

I wanted to continue training the model with the saved optimizer, but it crashed. The traceback is shown as follows: Traceback (most recent call last): File "lgesql/text2sql.py", line 105, in...

我是用官方的python代码进行模型推理， `asr_model.generate(filename,batch_size_s=300, merge_length_s=15, hotword='魔搭')` 发现第一个出现的进度显示rtf为0.831左右，按照代码逻辑, 这应该是vad model的处理效率？这是正常的吗？是否有可能对其进行加速呢？

ERROR occurs when running "tokenizer._tokenizer.model.clear_cache()"

2

I met an OOM problem when using BertTokenizer as https://github.com/huggingface/tokenizers/issues/1539 reports. Then I use tokenizer._tokenizer.model.clear_cache() or tokenizer._tokenizer.model._clear_cache() to clear cache. However, I met an error: AttributeError: 'tokenizers.models.WordPiece' object has no...