From 3958472fb2a9bbac5cb2a30e3fb11925c7b5d3d8 Mon Sep 17 00:00:00 2001
From: Yabin Li <wucong.lyb@alibaba-inc.com>
Date: 星期三, 20 三月 2024 19:21:33 +0800
Subject: [PATCH] Update SDK_advanced_guide_offline_en_zh.md
---
funasr/auto/auto_model.py | 14 +++++++-------
1 files changed, 7 insertions(+), 7 deletions(-)
diff --git a/funasr/auto/auto_model.py b/funasr/auto/auto_model.py
index 39f91e9..bd786d0 100644
--- a/funasr/auto/auto_model.py
+++ b/funasr/auto/auto_model.py
@@ -106,9 +106,9 @@
# if vad_model is not None, build vad model else None
vad_model = kwargs.get("vad_model", None)
+ vad_kwargs = {} if kwargs.get("vad_kwargs", {}) is None else kwargs.get("vad_kwargs", {})
if vad_model is not None:
logging.info("Building VAD model.")
- vad_kwargs = {} if kwargs.get("vad_kwargs", {}) is None else kwargs.get("vad_kwargs", {})
vad_kwargs["model"] = vad_model
vad_kwargs["model_revision"] = kwargs.get("vad_model_revision", None)
vad_kwargs["device"] = kwargs["device"]
@@ -116,10 +116,9 @@
# if punc_model is not None, build punc model else None
punc_model = kwargs.get("punc_model", None)
-
+ punc_kwargs = {} if kwargs.get("punc_kwargs", {}) is None else kwargs.get("punc_kwargs", {})
if punc_model is not None:
logging.info("Building punc model.")
- punc_kwargs = {} if kwargs.get("punc_kwargs", {}) is None else kwargs.get("punc_kwargs", {})
punc_kwargs["model"] = punc_model
punc_kwargs["model_revision"] = kwargs.get("punc_model_revision", None)
punc_kwargs["device"] = kwargs["device"]
@@ -127,10 +126,9 @@
# if spk_model is not None, build spk model else None
spk_model = kwargs.get("spk_model", None)
- spk_kwargs = kwargs.get("spk_model_revision", None)
+ spk_kwargs = {} if kwargs.get("spk_kwargs", {}) is None else kwargs.get("spk_kwargs", {})
if spk_model is not None:
logging.info("Building SPK model.")
- spk_kwargs = {} if kwargs.get("spk_kwargs", {}) is None else kwargs.get("spk_kwargs", {})
spk_kwargs["model"] = spk_model
spk_kwargs["model_revision"] = kwargs.get("spk_model_revision", None)
spk_kwargs["device"] = kwargs["device"]
@@ -189,7 +187,8 @@
kwargs["frontend"] = frontend
# build model
model_class = tables.model_classes.get(kwargs["model"])
- model_conf = kwargs.get("model_conf", {})
+ model_conf = {}
+ deep_update(model_conf, kwargs.get("model_conf", {}))
deep_update(model_conf, kwargs)
model = model_class(**model_conf, vocab_size=vocab_size)
model.to(device)
@@ -313,7 +312,8 @@
key = res[i]["key"]
vadsegments = res[i]["value"]
input_i = data_list[i]
- speech = load_audio_text_image_video(input_i, fs=kwargs["frontend"].fs, audio_fs=kwargs.get("fs", 16000))
+ fs = kwargs["frontend"].fs if hasattr(kwargs["frontend"], "fs") else 16000
+ speech = load_audio_text_image_video(input_i, fs=fs, audio_fs=kwargs.get("fs", 16000))
speech_lengths = len(speech)
n = len(vadsegments)
data_with_index = [(vadsegments[i], i) for i in range(n)]
--
Gitblit v1.9.1