From 21b0b0d2d2fefe00fbd9351a3375d93d10a0f420 Mon Sep 17 00:00:00 2001
From: zhifu gao <zhifu.gzf@alibaba-inc.com>
Date: 星期四, 30 三月 2023 21:17:27 +0800
Subject: [PATCH] Merge pull request #319 from alibaba-damo-academy/dev_lhn
---
funasr/bin/asr_inference_paraformer_streaming.py | 18 ++++++++++++++++++
1 files changed, 18 insertions(+), 0 deletions(-)
diff --git a/funasr/bin/asr_inference_paraformer_streaming.py b/funasr/bin/asr_inference_paraformer_streaming.py
index df590df..66dec39 100644
--- a/funasr/bin/asr_inference_paraformer_streaming.py
+++ b/funasr/bin/asr_inference_paraformer_streaming.py
@@ -581,7 +581,22 @@
speech2text = Speech2TextExport(**speech2text_kwargs)
else:
speech2text = Speech2Text(**speech2text_kwargs)
+
+ def _load_bytes(input):
+ middle_data = np.frombuffer(input, dtype=np.int16)
+ middle_data = np.asarray(middle_data)
+ if middle_data.dtype.kind not in 'iu':
+ raise TypeError("'middle_data' must be an array of integers")
+ dtype = np.dtype('float32')
+ if dtype.kind != 'f':
+ raise TypeError("'dtype' must be a floating point type")
+ i = np.iinfo(middle_data.dtype)
+ abs_max = 2 ** (i.bits - 1)
+ offset = i.min + abs_max
+ array = np.frombuffer((middle_data.astype(dtype) - offset) / abs_max, dtype=np.float32)
+ return array
+
def _forward(
data_path_and_name_and_type,
raw_inputs: Union[np.ndarray, torch.Tensor] = None,
@@ -592,6 +607,9 @@
):
# 3. Build data-iterator
+ if data_path_and_name_and_type is not None and data_path_and_name_and_type[2] == "bytes":
+ raw_inputs = _load_bytes(data_path_and_name_and_type[0])
+ raw_inputs = torch.tensor(raw_inputs)
if data_path_and_name_and_type is None and raw_inputs is not None:
if isinstance(raw_inputs, np.ndarray):
raw_inputs = torch.tensor(raw_inputs)
--
Gitblit v1.9.1