From 3d9f094e9652d4b84894c6fd4eae39a4a753b0f0 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期二, 16 五月 2023 23:48:00 +0800
Subject: [PATCH] train
---
funasr/models/e2e_vad.py | 74 +++++++++++++++++++++++++++++++++++--
1 files changed, 70 insertions(+), 4 deletions(-)
diff --git a/funasr/models/e2e_vad.py b/funasr/models/e2e_vad.py
old mode 100755
new mode 100644
index b9be89a..82d8422
--- 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
@@ -192,7 +212,12 @@
class E2EVadModel(nn.Module):
- def __init__(self, encoder: FSMN, vad_post_args: Dict[str, Any]):
+ """
+ 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)
self.windows_detector = WindowDetector(self.vad_opts.window_size_ms,
@@ -215,6 +240,7 @@
self.sil_pdf_ids = self.vad_opts.sil_pdf_ids
self.noise_average_decibel = -100.0
self.pre_end_silence_detected = False
+ self.next_seg = True
self.output_data_buf = []
self.output_data_buf_offset = 0
@@ -228,6 +254,7 @@
self.data_buf_all = None
self.waveform = None
self.ResetDetection()
+ self.frontend = frontend
def AllResetDetection(self):
self.is_final = False
@@ -244,6 +271,7 @@
self.sil_pdf_ids = self.vad_opts.sil_pdf_ids
self.noise_average_decibel = -100.0
self.pre_end_silence_detected = False
+ self.next_seg = True
self.output_data_buf = []
self.output_data_buf_offset = 0
@@ -283,7 +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
@@ -457,8 +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)
@@ -470,6 +498,44 @@
self.AllResetDetection()
return segments, in_cache
+ def forward_online(self, feats: torch.Tensor, waveform: torch.tensor, in_cache: Dict[str, torch.Tensor] = dict(),
+ is_final: bool = False, max_end_sil: int = 800
+ ) -> Tuple[List[List[List[int]]], Dict[str, torch.Tensor]]:
+ self.max_end_sil_frame_cnt_thresh = max_end_sil - self.vad_opts.speech_to_sil_time_thres
+ self.waveform = waveform # compute decibel for each frame
+
+ self.ComputeScores(feats, in_cache)
+ self.ComputeDecibel()
+ if not is_final:
+ self.DetectCommonFrames()
+ else:
+ self.DetectLastFrames()
+ segments = []
+ for batch_num in range(0, feats.shape[0]): # only support batch_size = 1 now
+ 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:
+ continue
+ if not self.next_seg and not self.output_data_buf[i].contain_seg_end_point:
+ continue
+ start_ms = self.output_data_buf[i].start_ms if self.next_seg else -1
+ if self.output_data_buf[i].contain_seg_end_point:
+ end_ms = self.output_data_buf[i].end_ms
+ self.next_seg = True
+ self.output_data_buf_offset += 1
+ else:
+ end_ms = -1
+ self.next_seg = False
+ segment = [start_ms, end_ms]
+ segment_batch.append(segment)
+ if segment_batch:
+ segments.append(segment_batch)
+ if is_final:
+ # reset class variables and clear the dict for the next query
+ self.AllResetDetection()
+ return segments, in_cache
+
def DetectCommonFrames(self) -> int:
if self.vad_state_machine == VadStateMachine.kVadInStateEndPointDetected:
return 0
--
Gitblit v1.9.1