From 6e69d784e4814c3dbe35e8f70c6cf4b920c8b20b Mon Sep 17 00:00:00 2001
From: 天地 <tiandiweizun@gmail.com>
Date: 星期三, 19 三月 2025 23:10:13 +0800
Subject: [PATCH] 1. bug fix:list(mean)和list(var)，由于mean和var是numpy，导致写入到文件的格式错误，参考上面的话，大概率是list(mean.tolist())，其实外层list没有必要 (#2437)
---
funasr/models/sense_voice/model.py | 10 ++++++++--
1 files changed, 8 insertions(+), 2 deletions(-)
diff --git a/funasr/models/sense_voice/model.py b/funasr/models/sense_voice/model.py
index 945a301..7971cc1 100644
--- a/funasr/models/sense_voice/model.py
+++ b/funasr/models/sense_voice/model.py
@@ -919,14 +919,20 @@
timestamp = []
tokens = tokenizer.text2tokens(text)[4:]
+ token_back_to_id = tokenizer.tokens2ids(tokens)
+ token_ids = []
+ for tok_ls in token_back_to_id:
+ if tok_ls: token_ids.extend(tok_ls)
+ else: token_ids.append(124)
+
logits_speech = self.ctc.softmax(encoder_out)[i, 4 : encoder_out_lens[i].item(), :]
pred = logits_speech.argmax(-1).cpu()
logits_speech[pred == self.blank_id, self.blank_id] = 0
align = ctc_forced_align(
logits_speech.unsqueeze(0).float(),
- torch.Tensor(token_int[4:]).unsqueeze(0).long().to(logits_speech.device),
+ torch.Tensor(token_ids).unsqueeze(0).long().to(logits_speech.device),
(encoder_out_lens[i] - 4).long(),
- torch.tensor(len(token_int) - 4).unsqueeze(0).long().to(logits_speech.device),
+ torch.tensor(len(token_ids)).unsqueeze(0).long().to(logits_speech.device),
ignore_id=self.ignore_id,
)
pred = groupby(align[0, : encoder_out_lens[i]])
--
Gitblit v1.9.1