From 6927d0baa7bcb2c86ec5e2517cb652e98e398f97 Mon Sep 17 00:00:00 2001
From: 雾聪 <wucong.lyb@alibaba-inc.com>
Date: 星期三, 14 六月 2023 00:34:42 +0800
Subject: [PATCH] rename websocket client&server; fix funasr-ws-client; update readme;
---
funasr/models/e2e_vad.py | 34 ++++++++++++++++++++--------------
1 files changed, 20 insertions(+), 14 deletions(-)
diff --git a/funasr/models/e2e_vad.py b/funasr/models/e2e_vad.py
index e477750..14d56a8 100644
--- a/funasr/models/e2e_vad.py
+++ b/funasr/models/e2e_vad.py
@@ -40,7 +40,6 @@
Deep-FSMN for Large Vocabulary Continuous Speech Recognition
https://arxiv.org/abs/1803.05030
"""
-
def __init__(
self,
sample_rate: int = 16000,
@@ -110,7 +109,6 @@
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
@@ -134,7 +132,6 @@
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
@@ -149,7 +146,6 @@
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
@@ -221,7 +217,6 @@
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)
@@ -231,7 +226,6 @@
self.vad_opts.frame_in_ms)
self.encoder = encoder
# init variables
- self.is_final = False
self.data_buf_start_frame = 0
self.frm_cnt = 0
self.latest_confirmed_speech_frame = 0
@@ -258,11 +252,10 @@
self.data_buf = None
self.data_buf_all = None
self.waveform = None
- self.ResetDetection()
self.frontend = frontend
+ self.last_drop_frames = 0
def AllResetDetection(self):
- self.is_final = False
self.data_buf_start_frame = 0
self.frm_cnt = 0
self.latest_confirmed_speech_frame = 0
@@ -289,7 +282,8 @@
self.data_buf = None
self.data_buf_all = None
self.waveform = None
- self.ResetDetection()
+ self.last_drop_frames = 0
+ self.windows_detector.Reset()
def ResetDetection(self):
self.continous_silence_frame_count = 0
@@ -301,6 +295,15 @@
self.windows_detector.Reset()
self.sil_frame = 0
self.frame_probs = []
+
+ if self.output_data_buf:
+ assert self.output_data_buf[-1].contain_seg_end_point == True
+ drop_frames = int(self.output_data_buf[-1].end_ms / self.vad_opts.frame_in_ms)
+ real_drop_frames = drop_frames - self.last_drop_frames
+ self.last_drop_frames = drop_frames
+ self.data_buf_all = self.data_buf_all[real_drop_frames * int(self.vad_opts.frame_in_ms * self.vad_opts.sample_rate / 1000):]
+ self.decibel = self.decibel[real_drop_frames:]
+ self.scores = self.scores[:, real_drop_frames:, :]
def ComputeDecibel(self) -> None:
frame_sample_length = int(self.vad_opts.frame_length_ms * self.vad_opts.sample_rate / 1000)
@@ -329,7 +332,7 @@
while self.data_buf_start_frame < frame_idx:
if len(self.data_buf) >= int(self.vad_opts.frame_in_ms * self.vad_opts.sample_rate / 1000):
self.data_buf_start_frame += 1
- self.data_buf = self.data_buf_all[self.data_buf_start_frame * int(
+ self.data_buf = self.data_buf_all[(self.data_buf_start_frame - self.last_drop_frames) * int(
self.vad_opts.frame_in_ms * self.vad_opts.sample_rate / 1000):]
def PopDataToOutputBuf(self, start_frm: int, frm_cnt: int, first_frm_is_start_point: bool,
@@ -478,6 +481,8 @@
def forward(self, feats: torch.Tensor, waveform: torch.tensor, in_cache: Dict[str, torch.Tensor] = dict(),
is_final: bool = False
) -> Tuple[List[List[List[int]]], Dict[str, torch.Tensor]]:
+ if not in_cache:
+ self.AllResetDetection()
self.waveform = waveform # compute decibel for each frame
self.ComputeDecibel()
self.ComputeScores(feats, in_cache)
@@ -490,8 +495,7 @@
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 is_final and (
- not self.output_data_buf[i].contain_seg_start_point or not self.output_data_buf[
+ 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]
@@ -507,6 +511,8 @@
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]]:
+ if not in_cache:
+ self.AllResetDetection()
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
@@ -547,7 +553,7 @@
return 0
for i in range(self.vad_opts.nn_eval_block_size - 1, -1, -1):
frame_state = FrameState.kFrameStateInvalid
- frame_state = self.GetFrameState(self.frm_cnt - 1 - i)
+ frame_state = self.GetFrameState(self.frm_cnt - 1 - i - self.last_drop_frames)
self.DetectOneFrame(frame_state, self.frm_cnt - 1 - i, False)
return 0
@@ -557,7 +563,7 @@
return 0
for i in range(self.vad_opts.nn_eval_block_size - 1, -1, -1):
frame_state = FrameState.kFrameStateInvalid
- frame_state = self.GetFrameState(self.frm_cnt - 1 - i)
+ frame_state = self.GetFrameState(self.frm_cnt - 1 - i - self.last_drop_frames)
if i != 0:
self.DetectOneFrame(frame_state, self.frm_cnt - 1 - i, False)
else:
--
Gitblit v1.9.1