From d878df49fdccebd21ce7752643b35d995bafcf55 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期四, 22 二月 2024 13:08:14 +0800
Subject: [PATCH] v1.0.10
---
funasr/models/paraformer/model.py | 22 +++++++++++++---------
1 files changed, 13 insertions(+), 9 deletions(-)
diff --git a/funasr/models/paraformer/model.py b/funasr/models/paraformer/model.py
index 468d23f..90ce162 100644
--- a/funasr/models/paraformer/model.py
+++ b/funasr/models/paraformer/model.py
@@ -451,11 +451,13 @@
self.nbest = kwargs.get("nbest", 1)
meta_data = {}
- if isinstance(data_in, torch.Tensor): # fbank
+ if isinstance(data_in, torch.Tensor) and kwargs.get("data_type", "sound") == "fbank": # fbank
speech, speech_lengths = data_in, data_lengths
if len(speech.shape) < 3:
speech = speech[None, :, :]
- if speech_lengths is None:
+ if speech_lengths is not None:
+ speech_lengths = speech_lengths.squeeze(-1)
+ else:
speech_lengths = speech.shape[1]
else:
# extract fbank feats
@@ -491,6 +493,8 @@
b, n, d = decoder_out.size()
if isinstance(key[0], (list, tuple)):
key = key[0]
+ if len(key) < b:
+ key = key*b
for i in range(b):
x = encoder_out[i, :encoder_out_lens[i], :]
am_scores = decoder_out[i, :pre_token_length[i], :]
@@ -512,9 +516,10 @@
nbest_hyps = [Hypothesis(yseq=yseq, score=score)]
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):
@@ -528,13 +533,12 @@
if tokenizer is not None:
# Change integer-ids to tokens
token = tokenizer.ids2tokens(token_int)
- text = tokenizer.tokens2text(token)
-
- text_postprocessed, _ = postprocess_utils.sentence_postprocess(token)
+ text_postprocessed = tokenizer.tokens2text(token)
+ if not hasattr(tokenizer, "bpemodel"):
+ text_postprocessed, _ = postprocess_utils.sentence_postprocess(token)
result_i = {"key": key[i], "text": text_postprocessed}
-
if ibest_writer is not None:
ibest_writer["token"][key[i]] = " ".join(token)
# ibest_writer["text"][key[i]] = text
--
Gitblit v1.9.1