From a1cbcc09f4e99ffac0a7bee93775c9166cb66787 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期五, 12 五月 2023 10:43:03 +0800
Subject: [PATCH] onnx export funasr_onnx
---
funasr/runtime/python/onnxruntime/funasr_onnx/paraformer_bin.py | 30 +++++++++++++++++++++++++++---
1 files changed, 27 insertions(+), 3 deletions(-)
diff --git a/funasr/runtime/python/onnxruntime/funasr_onnx/paraformer_bin.py b/funasr/runtime/python/onnxruntime/funasr_onnx/paraformer_bin.py
index cbdb8d9..7525c90 100644
--- a/funasr/runtime/python/onnxruntime/funasr_onnx/paraformer_bin.py
+++ b/funasr/runtime/python/onnxruntime/funasr_onnx/paraformer_bin.py
@@ -1,4 +1,6 @@
# -*- encoding: utf-8 -*-
+# Copyright FunASR (https://github.com/alibaba-damo-academy/FunASR). All Rights Reserved.
+# MIT License (https://opensource.org/licenses/MIT)
import os.path
from pathlib import Path
@@ -19,17 +21,36 @@
class Paraformer():
+ """
+ Author: Speech Lab of DAMO Academy, Alibaba Group
+ Paraformer: Fast and Accurate Parallel Transformer for Non-autoregressive End-to-End Speech Recognition
+ https://arxiv.org/abs/2206.08317
+ """
def __init__(self, model_dir: Union[str, Path] = None,
batch_size: int = 1,
device_id: Union[str, int] = "-1",
plot_timestamp_to: str = "",
- pred_bias: int = 1,
quantize: bool = False,
intra_op_num_threads: int = 4,
+ cache_dir=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)
+ 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)
+
+
model_file = os.path.join(model_dir, 'model.onnx')
if quantize:
@@ -47,7 +68,10 @@
self.ort_infer = OrtInferSession(model_file, device_id, intra_op_num_threads=intra_op_num_threads)
self.batch_size = batch_size
self.plot_timestamp_to = plot_timestamp_to
- self.pred_bias = pred_bias
+ if "predictor_bias" in config['model_conf'].keys():
+ self.pred_bias = config['model_conf']['predictor_bias']
+ else:
+ self.pred_bias = 0
def __call__(self, wav_content: Union[str, np.ndarray, List[str]], **kwargs) -> List:
waveform_list = self.load_data(wav_content, self.frontend.opts.frame_opts.samp_freq)
--
Gitblit v1.9.1