xliucs

some detail of gector-large

2

@MaksTarnavskyi I am interested in your paper “Ensembling and Knowledge Distilling of Large Sequence Taggers for Grammatical Error Correction” and I want to reproduce your results. However, I have some...

[Bug Report] Load model to mutilple devices

7

When I use the following code to load LLama2 and generate: ```python model = HookedTransformer.from_pretrained("meta-llama/Llama-2-7b-chat-hf", hf_model=hf_model, device="cuda", n_devices=4, move_to_device=True, fold_ln=False, center_writing_weights=False, center_unembed=False, tokenizer=tokenizer) model.generate("The capital of Germany is", max_new_tokens=20, temperature=0)...

phonetic预训练细节

8

论文里面说使用带错误的训练数据预训练phonetic Encoder， 但代码里面好像是用的纠正后的数据，不知道我有没有理解错，恳请解惑 

您好，我们对您的工作很感兴趣，想问一下在数据准备时，N个错误的句子重复N次这一步，您是人工做的还是自动化处理的呢？

中文音色训练

23

使用10h左右中文数据进行训练，语言选择的 ZH_MIX_EN，训练之后在某些字的发音上有些奇怪，比如“我好想你”的“想”会发一声，请问有什么见解吗

I met this: NotImplementedError: Converter is not implemented (OperationDescription(domain='', operation_type='GreaterOrEqual', version=16))

Is there a limit on the size of a single serialized object?

1

I got this error: ``` Traceback (most recent call last): File "/user/liuxin/workspace/modelbest-audio-dataset/modelbest_audio_dataset/datasets/passage_level/scripts/wuxi/test_pipeline/simple_demucs_44k_test.py", line 326, in main_cli() File "/user/liuxin/workspace/modelbest-audio-dataset/modelbest_audio_dataset/datasets/passage_level/scripts/wuxi/test_pipeline/simple_demucs_44k_test.py", line 322, in main_cli to_sstable(args.src_partition, args.tgt_partition, args.limit) File "/user/liuxin/workspace/modelbest-audio-dataset/modelbest_audio_dataset/datasets/passage_level/scripts/wuxi/test_pipeline/simple_demucs_44k_test.py", line 293, in...