From 94de39dde2e616a01683c518023d0fab72b4e103 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期一, 19 二月 2024 22:21:50 +0800
Subject: [PATCH] aishell example
---
funasr/models/paraformer/model.py | 10 ++++++----
1 files changed, 6 insertions(+), 4 deletions(-)
diff --git a/funasr/models/paraformer/model.py b/funasr/models/paraformer/model.py
index 468d23f..7747146 100644
--- a/funasr/models/paraformer/model.py
+++ b/funasr/models/paraformer/model.py
@@ -451,7 +451,7 @@
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, :, :]
@@ -491,6 +491,8 @@
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], :]
@@ -528,9 +530,9 @@
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}
--
Gitblit v1.9.1