From 37d6930561f4e798e76f81c37d912906c97b6bea Mon Sep 17 00:00:00 2001
From: pointerhacker <145901472+pointerhacker@users.noreply.github.com>
Date: 星期三, 20 十一月 2024 18:39:05 +0800
Subject: [PATCH] fix:添加音频码率验证以防止模型异常 (#2219)
---
funasr/auto/auto_model.py | 12 +++++++-----
1 files changed, 7 insertions(+), 5 deletions(-)
diff --git a/funasr/auto/auto_model.py b/funasr/auto/auto_model.py
index 9f5f4fb..08308a2 100644
--- a/funasr/auto/auto_model.py
+++ b/funasr/auto/auto_model.py
@@ -147,13 +147,14 @@
# if spk_model is not None, build spk model else None
spk_model = kwargs.get("spk_model", None)
spk_kwargs = {} if kwargs.get("spk_kwargs", {}) is None else kwargs.get("spk_kwargs", {})
+ cb_kwargs = {} if spk_kwargs.get("cb_kwargs", {}) is None else spk_kwargs.get("cb_kwargs", {})
if spk_model is not None:
logging.info("Building SPK model.")
spk_kwargs["model"] = spk_model
spk_kwargs["model_revision"] = kwargs.get("spk_model_revision", "master")
spk_kwargs["device"] = kwargs["device"]
spk_model, spk_kwargs = self.build_model(**spk_kwargs)
- self.cb_model = ClusterBackend().to(kwargs["device"])
+ self.cb_model = ClusterBackend(**cb_kwargs).to(kwargs["device"])
spk_mode = kwargs.get("spk_mode", "punc_segment")
if spk_mode not in ["default", "vad_segment", "punc_segment"]:
logging.error("spk_mode should be one of default, vad_segment and punc_segment.")
@@ -199,6 +200,7 @@
tokenizers_build = []
vocab_sizes = []
token_lists = []
+
### === only for kws ===
token_list_files = kwargs.get("token_lists", [])
seg_dicts = kwargs.get("seg_dicts", [])
@@ -213,9 +215,9 @@
### === only for kws ===
if len(token_list_files) > 1:
- tokenizer_conf.token_list = token_list_files[i]
+ tokenizer_conf["token_list"] = token_list_files[i]
if len(seg_dicts) > 1:
- tokenizer_conf.seg_dict = seg_dicts[i]
+ tokenizer_conf["seg_dict"] = seg_dicts[i]
### === only for kws ===
tokenizer = tokenizer_class(**tokenizer_conf)
@@ -228,8 +230,8 @@
if token_list is not None:
vocab_size = len(token_list)
- if vocab_size == -1 and hasattr(tokenizer, "get_vocab_size"):
- vocab_size = tokenizer.get_vocab_size()
+ if vocab_size == -1 and hasattr(tokenizer, "get_vocab_size"):
+ vocab_size = tokenizer.get_vocab_size()
token_lists.append(token_list)
vocab_sizes.append(vocab_size)
--
Gitblit v1.9.1