From b15db52e4e67da8a133a67e8ffa415386de48b40 Mon Sep 17 00:00:00 2001
From: zhuyunfeng <10596244@qq.com>
Date: 星期二, 09 五月 2023 23:03:15 +0800
Subject: [PATCH] Add contributor
---
funasr/models/e2e_vad.py | 31 ++++++++++++++++++++++++++++---
1 files changed, 28 insertions(+), 3 deletions(-)
diff --git a/funasr/models/e2e_vad.py b/funasr/models/e2e_vad.py
index ff37429..d72c635 100644
--- a/funasr/models/e2e_vad.py
+++ b/funasr/models/e2e_vad.py
@@ -35,6 +35,11 @@
class VADXOptions:
+ """
+ Author: Speech Lab of DAMO Academy, Alibaba Group
+ Deep-FSMN for Large Vocabulary Continuous Speech Recognition
+ https://arxiv.org/abs/1803.05030
+ """
def __init__(
self,
sample_rate: int = 16000,
@@ -99,6 +104,11 @@
class E2EVadSpeechBufWithDoa(object):
+ """
+ Author: Speech Lab of DAMO Academy, Alibaba Group
+ Deep-FSMN for Large Vocabulary Continuous Speech Recognition
+ https://arxiv.org/abs/1803.05030
+ """
def __init__(self):
self.start_ms = 0
self.end_ms = 0
@@ -117,6 +127,11 @@
class E2EVadFrameProb(object):
+ """
+ Author: Speech Lab of DAMO Academy, Alibaba Group
+ Deep-FSMN for Large Vocabulary Continuous Speech Recognition
+ https://arxiv.org/abs/1803.05030
+ """
def __init__(self):
self.noise_prob = 0.0
self.speech_prob = 0.0
@@ -126,6 +141,11 @@
class WindowDetector(object):
+ """
+ Author: Speech Lab of DAMO Academy, Alibaba Group
+ Deep-FSMN for Large Vocabulary Continuous Speech Recognition
+ https://arxiv.org/abs/1803.05030
+ """
def __init__(self, window_size_ms: int, sil_to_speech_time: int,
speech_to_sil_time: int, frame_size_ms: int):
self.window_size_ms = window_size_ms
@@ -192,6 +212,11 @@
class E2EVadModel(nn.Module):
+ """
+ Author: Speech Lab of DAMO Academy, Alibaba Group
+ Deep-FSMN for Large Vocabulary Continuous Speech Recognition
+ https://arxiv.org/abs/1803.05030
+ """
def __init__(self, encoder: FSMN, vad_post_args: Dict[str, Any], frontend=None):
super(E2EVadModel, self).__init__()
self.vad_opts = VADXOptions(**vad_post_args)
@@ -286,7 +311,7 @@
0.000001))
def ComputeScores(self, feats: torch.Tensor, in_cache: Dict[str, torch.Tensor]) -> None:
- scores = self.encoder(feats, in_cache) # return B * T * D
+ scores = self.encoder(feats, in_cache).to('cpu') # return B * T * D
assert scores.shape[1] == feats.shape[1], "The shape between feats and scores does not match"
self.vad_opts.nn_eval_block_size = scores.shape[1]
self.frm_cnt += scores.shape[1] # count total frames
@@ -460,8 +485,8 @@
segment_batch = []
if len(self.output_data_buf) > 0:
for i in range(self.output_data_buf_offset, len(self.output_data_buf)):
- if not self.output_data_buf[i].contain_seg_start_point or not self.output_data_buf[
- i].contain_seg_end_point:
+ if not is_final and (not self.output_data_buf[i].contain_seg_start_point or not self.output_data_buf[
+ i].contain_seg_end_point):
continue
segment = [self.output_data_buf[i].start_ms, self.output_data_buf[i].end_ms]
segment_batch.append(segment)
--
Gitblit v1.9.1