From 807a3acdbb6511dab3b5af5e952ef5a8fe231c99 Mon Sep 17 00:00:00 2001
From: 雾聪 <wucong.lyb@alibaba-inc.com>
Date: 星期日, 03 三月 2024 20:37:29 +0800
Subject: [PATCH] update readme
---
funasr/models/transformer/model.py | 15 +++++++++------
1 files changed, 9 insertions(+), 6 deletions(-)
diff --git a/funasr/models/transformer/model.py b/funasr/models/transformer/model.py
index 4ad466b..c68ccd7 100644
--- a/funasr/models/transformer/model.py
+++ b/funasr/models/transformer/model.py
@@ -118,6 +118,7 @@
# token_list, sym_space, sym_blank, report_cer, report_wer
# )
#
+ self.error_calculator = None
if ctc_weight == 0.0:
self.ctc = None
else:
@@ -422,9 +423,11 @@
for nbest_idx, hyp in enumerate(nbest_hyps):
ibest_writer = None
- if ibest_writer is None and kwargs.get("output_dir") is not None:
- writer = DatadirWriter(kwargs.get("output_dir"))
- ibest_writer = writer[f"{nbest_idx+1}best_recog"]
+ if kwargs.get("output_dir") is not None:
+ if not hasattr(self, "writer"):
+ self.writer = DatadirWriter(kwargs.get("output_dir"))
+ ibest_writer = self.writer[f"{nbest_idx + 1}best_recog"]
+
# remove sos/eos and get results
last_pos = -1
if isinstance(hyp.yseq, list):
@@ -439,13 +442,13 @@
token = tokenizer.ids2tokens(token_int)
text = tokenizer.tokens2text(token)
- # text_postprocessed, _ = postprocess_utils.sentence_postprocess(token)
- result_i = {"key": key[i], "token": token, "text": text}
+ text_postprocessed, _ = postprocess_utils.sentence_postprocess(token)
+ result_i = {"key": key[i], "token": token, "text": text_postprocessed}
results.append(result_i)
if ibest_writer is not None:
ibest_writer["token"][key[i]] = " ".join(token)
- ibest_writer["text"][key[i]] = text
+ ibest_writer["text"][key[i]] = text_postprocessed
return results, meta_data
--
Gitblit v1.9.1