python/FunASR-XL.git

FUNASR训练

parent: 4482bbcb | 补丁 | 提交 | ignore whitespace

zhifu gao

2024-03-21 cd001acf68f128245628667dc69c676104b2f438

Dev gzf train (#1524)

* trainer

* trainer

* trainer

* trainer

* trainer

* trainer

* trainer

* trainer

* trainer

* trainer

* trainer

* trainer

* trainer

* trainer

* trainer

* trainer

* train (#1521) (#1522)

* trainer

* trainer

* trainer

* trainer

* trainer

* trainer

* trainer

* trainer

* trainer

* trainer

* trainer

* trainer

* trainer

* trainer

* trainer

* trainer

* trainer

* trainer

2个文件已修改

	funasr/models/paraformer/decoder.py	4 ●●●●● 补丁 \| 查看 \| 原始文档 \| blame \| 历史
	funasr/utils/misc.py	1 ●●●●● 补丁 \| 查看 \| 原始文档 \| blame \| 历史

 funasr/models/paraformer/decoder.py

@@ -351,9 +351,9 @@
        hlens: torch.Tensor,
        ys_in_pad: torch.Tensor,
        ys_in_lens: torch.Tensor,
        return_hidden: bool = False,
        return_both: bool= False,
        chunk_mask: torch.Tensor = None,
        return_hidden: bool = False,
        return_both: bool = False,
    ) -> Tuple[torch.Tensor, torch.Tensor]:
        """Forward decoder.


 funasr/utils/misc.py

@@ -1,6 +1,7 @@
import os
import io
import shutil
import logging
from collections import OrderedDict
import numpy as np
from omegaconf import DictConfig, OmegaConf

			@@ -351,9 +351,9 @@
			hlens: torch.Tensor,
			ys_in_pad: torch.Tensor,
			ys_in_lens: torch.Tensor,
			return_hidden: bool = False,
			return_both: bool= False,
			chunk_mask: torch.Tensor = None,
			return_hidden: bool = False,
			return_both: bool = False,
			) -> Tuple[torch.Tensor, torch.Tensor]:
			"""Forward decoder.

			@@ -1,6 +1,7 @@
			import os
			import io
			import shutil
			import logging
			from collections import OrderedDict
			import numpy as np
			from omegaconf import DictConfig, OmegaConf