Patch decoding for PC models (#6630) (#6631)

* Patch decoding logic for PC models * Patch decoding logic for PC models --------- Signed-off-by: smajumdar <[email protected]> Co-authored-by: Somshubra Majumdar <[email protected]>
NVIDIA · May 26, 2023 · 67b1906 · 67b1906
1 parent 4b363ce
commit 67b1906
Show file tree

Hide file tree

Showing 2 changed files with 10 additions and 0 deletions.
diff --git a/nemo/collections/asr/metrics/rnnt_wer.py b/nemo/collections/asr/metrics/rnnt_wer.py
@@ -13,6 +13,7 @@
 # limitations under the License.
 
 import copy
+import re
 from abc import abstractmethod
 from dataclasses import dataclass, is_dataclass
 from typing import Callable, Dict, List, Optional, Tuple, Union
@@ -499,6 +500,10 @@ def decode_hypothesis(self, hypotheses_list: List[Hypothesis]) -> List[Union[Hyp
             else:
                 hypothesis = self.decode_tokens_to_str(prediction)
 
+                # TODO: remove
+                # collapse leading spaces before . , ? for PC models
+                hypothesis = re.sub(r'(\s+)([\.\,\?])', r'\2', hypothesis)
+
                 if self.compute_hypothesis_token_set:
                     hypotheses_list[ind].tokens = self.decode_ids_to_tokens(prediction)
 

diff --git a/nemo/collections/asr/metrics/wer.py b/nemo/collections/asr/metrics/wer.py
@@ -12,6 +12,7 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
+import re
 from abc import abstractmethod
 from dataclasses import dataclass, is_dataclass
 from typing import Callable, Dict, List, Optional, Tuple, Union
@@ -540,6 +541,10 @@ def decode_hypothesis(
             else:
                 hypothesis = self.decode_tokens_to_str(decoded_prediction)
 
+                # TODO: remove
+                # collapse leading spaces before . , ? for PC models
+                hypothesis = re.sub(r'(\s+)([\.\,\?])', r'\2', hypothesis)
+
             # Preserve this wrapped hypothesis or decoded text tokens.
             hypotheses_list[ind].text = hypothesis