From 6fa8ee48e117fa9c3bef450e02776e8c26b278e7 Mon Sep 17 00:00:00 2001
From: zhifu gao <zhifu.gzf@alibaba-inc.com>
Date: 星期六, 30 三月 2024 10:13:42 +0800
Subject: [PATCH] Dev gzf new (#1567)
---
funasr/auto/auto_model.py | 25 +++++++++++++------------
1 files changed, 13 insertions(+), 12 deletions(-)
diff --git a/funasr/auto/auto_model.py b/funasr/auto/auto_model.py
index 39f91e9..7adaae2 100644
--- a/funasr/auto/auto_model.py
+++ b/funasr/auto/auto_model.py
@@ -25,11 +25,12 @@
from funasr.train_utils.set_all_random_seed import set_all_random_seed
from funasr.train_utils.load_pretrained_model import load_pretrained_model
from funasr.utils import export_utils
+
try:
from funasr.models.campplus.utils import sv_chunk, postprocess, distribute_spk
from funasr.models.campplus.cluster_backend import ClusterBackend
except:
- print("Notice: If you want to use the speaker diarization, please `pip install hdbscan`")
+ pass
def prepare_data_iterator(data_in, input_len=None, data_type=None, key=None):
@@ -106,33 +107,31 @@
# 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["model_revision"] = kwargs.get("vad_model_revision", "master")
vad_kwargs["device"] = kwargs["device"]
vad_model, vad_kwargs = self.build_model(**vad_kwargs)
# 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["model_revision"] = kwargs.get("punc_model_revision", "master")
punc_kwargs["device"] = kwargs["device"]
punc_model, punc_kwargs = self.build_model(**punc_kwargs)
# 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["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"])
@@ -189,7 +188,8 @@
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)
@@ -202,7 +202,7 @@
load_pretrained_model(
model=model,
path=init_param,
- ignore_init_mismatch=kwargs.get("ignore_init_mismatch", False),
+ ignore_init_mismatch=kwargs.get("ignore_init_mismatch", True),
oss_bucket=kwargs.get("oss_bucket", None),
scope_map=kwargs.get("scope_map", []),
excludes=kwargs.get("excludes", None),
@@ -313,7 +313,8 @@
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