Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[ASR] Remove fluid api and useless import, test=asr #2944

Merged
merged 2 commits into from Feb 21, 2023
Merged

[ASR] Remove fluid api and useless import, test=asr #2944

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
e6a9d9b
remove fluid api and useless import.
zxcd Feb 21, 2023
0214bdb
fix variable name
zxcd Feb 21, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
1 change: 0 additions & 1 deletion paddlespeech/s2t/models/wav2vec2/wav2vec2_ASR.py
View file
Open in desktop
Expand Up @@ -12,7 +12,6 @@
# See the License for the specific language governing permissions and
# limitations under the License.
from collections import defaultdict
from turtle import Turtle
from typing import Dict
from typing import List
from typing import Tuple
Expand Down
6 changes: 3 additions & 3 deletions paddlespeech/s2t/training/gradclip.py
View file
Open in desktop
Expand Up @@ -56,15 +56,15 @@ def _dygraph_clip(self, params_grads):
if len(sum_square_list) == 0:
return params_grads

global_norm_var = layers.concat(sum_square_list)
global_norm_var = paddle.concat(sum_square_list)
global_norm_var = paddle.sum(global_norm_var)
global_norm_var = paddle.sqrt(global_norm_var)

# debug log
logger.debug(f"Grad Global Norm: {float(global_norm_var)}!!!!")

max_global_norm = layers.fill_constant(
shape=[1], dtype=global_norm_var.dtype, value=self.clip_norm)
max_global_norm = paddle.full(
shape=[1], dtype=global_norm_var.dtype, fill_value=self.clip_norm)
clip_var = paddle.divide(
x=max_global_norm,
y=paddle.maximum(x=global_norm_var, y=max_global_norm))
Expand Down