From c2dee5e3c29eba79e591d9e9caebaef15ea4e56b Mon Sep 17 00:00:00 2001
From: hnluo <haoneng.lhn@alibaba-inc.com>
Date: 星期四, 29 六月 2023 11:09:28 +0800
Subject: [PATCH] Merge pull request #687 from alibaba-damo-academy/dev_lhn
---
funasr/runtime/python/onnxruntime/funasr_onnx/punc_bin.py | 35 +++++++++++++++++++++++++++--------
1 files changed, 27 insertions(+), 8 deletions(-)
diff --git a/funasr/runtime/python/onnxruntime/funasr_onnx/punc_bin.py b/funasr/runtime/python/onnxruntime/funasr_onnx/punc_bin.py
index 6fd01e4..777de4f 100644
--- a/funasr/runtime/python/onnxruntime/funasr_onnx/punc_bin.py
+++ b/funasr/runtime/python/onnxruntime/funasr_onnx/punc_bin.py
@@ -24,15 +24,32 @@
batch_size: int = 1,
device_id: Union[str, int] = "-1",
quantize: bool = False,
- intra_op_num_threads: int = 4
+ intra_op_num_threads: int = 4,
+ cache_dir: str = None,
):
-
+
if not Path(model_dir).exists():
- raise FileNotFoundError(f'{model_dir} does not exist.')
-
+ from modelscope.hub.snapshot_download import snapshot_download
+ try:
+ model_dir = snapshot_download(model_dir, cache_dir=cache_dir)
+ except:
+ raise "model_dir must be model_name in modelscope or local path downloaded from modelscope, but is {}".format(
+ model_dir)
+
model_file = os.path.join(model_dir, 'model.onnx')
if quantize:
model_file = os.path.join(model_dir, 'model_quant.onnx')
+ if not os.path.exists(model_file):
+ print(".onnx is not exist, begin to export onnx")
+ from funasr.export.export_model import ModelExport
+ export_model = ModelExport(
+ cache_dir=cache_dir,
+ onnx=True,
+ device="cpu",
+ quant=quantize,
+ )
+ export_model.export(model_dir)
+
config_file = os.path.join(model_dir, 'punc.yaml')
config = read_yaml(config_file)
@@ -135,9 +152,10 @@
batch_size: int = 1,
device_id: Union[str, int] = "-1",
quantize: bool = False,
- intra_op_num_threads: int = 4
+ intra_op_num_threads: int = 4,
+ cache_dir: str = None
):
- super(CT_Transformer_VadRealtime, self).__init__(model_dir, batch_size, device_id, quantize, intra_op_num_threads)
+ super(CT_Transformer_VadRealtime, self).__init__(model_dir, batch_size, device_id, quantize, intra_op_num_threads, cache_dir=cache_dir)
def __call__(self, text: str, param_dict: map, split_size=20):
cache_key = "cache"
@@ -168,11 +186,12 @@
mini_sentence = cache_sent + mini_sentence
mini_sentence_id = np.concatenate((cache_sent_id, mini_sentence_id), axis=0,dtype='int32')
text_length = len(mini_sentence_id)
+ vad_mask = self.vad_mask(text_length, len(cache))[None, None, :, :].astype(np.float32)
data = {
"input": mini_sentence_id[None,:],
"text_lengths": np.array([text_length], dtype='int32'),
- "vad_mask": self.vad_mask(text_length, len(cache))[None, None, :, :].astype(np.float32),
- "sub_masks": np.tril(np.ones((text_length, text_length), dtype=np.float32))[None, None, :, :].astype(np.float32)
+ "vad_mask": vad_mask,
+ "sub_masks": vad_mask
}
try:
outputs = self.infer(data['input'], data['text_lengths'], data['vad_mask'], data["sub_masks"])
--
Gitblit v1.9.1