Update README.md
This commit is contained in:
parent
008e89880d
commit
e172cc3ffe
|
@ -113,7 +113,7 @@ After completing the above steps, the dataset directory will contain the preproc
|
||||||
|
|
||||||
* `keep_ckpts`: Keep the last `keep_ckpts` models during training. Set to `0` will keep them all. Default is `3`.
|
* `keep_ckpts`: Keep the last `keep_ckpts` models during training. Set to `0` will keep them all. Default is `3`.
|
||||||
|
|
||||||
* `all_in_mem`: Load all dataset to RAM. It can be enabled when the disk IO of some platforms is too low and the system memory is much larger than your dataset.
|
* `all_in_mem`: Load all dataset to RAM. It can be enabled when the disk IO of some platforms is too low and the system memory is **much larger** than your dataset.
|
||||||
|
|
||||||
## 🏋️♀️ Training
|
## 🏋️♀️ Training
|
||||||
|
|
||||||
|
|
|
@ -113,7 +113,7 @@ python preprocess_hubert_f0.py
|
||||||
|
|
||||||
* `keep_ckpts`:训练时保留最后几个模型,`0`为保留所有,默认只保留最后`3`个
|
* `keep_ckpts`:训练时保留最后几个模型,`0`为保留所有,默认只保留最后`3`个
|
||||||
|
|
||||||
* `all_in_mem`:加载所有数据集到内存中,某些平台的硬盘IO过于低下、同时内存容量*远大于*数据集体积时可以启用
|
* `all_in_mem`:加载所有数据集到内存中,某些平台的硬盘IO过于低下、同时内存容量 **远大于** 数据集体积时可以启用
|
||||||
|
|
||||||
## 🏋️♀️ 训练
|
## 🏋️♀️ 训练
|
||||||
|
|
||||||
|
|
Loading…
Reference in New Issue