From 28a19dbc4e85d3b8a4ec2ef7483bba64d422b43f Mon Sep 17 00:00:00 2001
From: aky15 <ankeyu.aky@11.17.44.249>
Date: 星期三, 12 四月 2023 18:03:06 +0800
Subject: [PATCH] Merge remote-tracking branch 'origin/main' into dev_aky
---
funasr/bin/vad_inference_online.py | 15 ++++++---------
1 files changed, 6 insertions(+), 9 deletions(-)
diff --git a/funasr/bin/vad_inference_online.py b/funasr/bin/vad_inference_online.py
index faee1fc..9ed0721 100644
--- a/funasr/bin/vad_inference_online.py
+++ b/funasr/bin/vad_inference_online.py
@@ -33,12 +33,6 @@
header_colors = '\033[95m'
end_colors = '\033[0m'
-global_asr_language: str = 'zh-cn'
-global_sample_rate: Union[int, Dict[Any, int]] = {
- 'audio_fs': 16000,
- 'model_fs': 16000
-}
-
class Speech2VadSegmentOnline(Speech2VadSegment):
"""Speech2VadSegmentOnline class
@@ -62,7 +56,7 @@
@torch.no_grad()
def __call__(
self, speech: Union[torch.Tensor, np.ndarray], speech_lengths: Union[torch.Tensor, np.ndarray] = None,
- in_cache: Dict[str, torch.Tensor] = dict(), is_final: bool = False
+ in_cache: Dict[str, torch.Tensor] = dict(), is_final: bool = False, max_end_sil: int = 800
) -> Tuple[torch.Tensor, List[List[int]], torch.Tensor]:
"""Inference
@@ -93,7 +87,8 @@
"feats": feats,
"waveform": waveforms,
"in_cache": in_cache,
- "is_final": is_final
+ "is_final": is_final,
+ "max_end_sil": max_end_sil
}
# a. To device
batch = to_device(batch, device=self.device)
@@ -223,7 +218,8 @@
vad_results = []
batch_in_cache = param_dict['in_cache'] if param_dict is not None else dict()
- is_final = param_dict['is_final'] if param_dict is not None else False
+ is_final = param_dict.get('is_final', False) if param_dict is not None else False
+ max_end_sil = param_dict.get('max_end_sil', 800) if param_dict is not None else 800
for keys, batch in loader:
assert isinstance(batch, dict), type(batch)
assert all(isinstance(s, str) for s in keys), keys
@@ -231,6 +227,7 @@
assert len(keys) == _bs, f"{len(keys)} != {_bs}"
batch['in_cache'] = batch_in_cache
batch['is_final'] = is_final
+ batch['max_end_sil'] = max_end_sil
# do vad segment
_, results, param_dict['in_cache'] = speech2vadsegment(**batch)
--
Gitblit v1.9.1