From 20b8e4e2011ff6b829cab8380bb90a6cb3b86a41 Mon Sep 17 00:00:00 2001
From: zhifu gao <zhifu.gzf@alibaba-inc.com>
Date: 星期三, 15 三月 2023 19:10:31 +0800
Subject: [PATCH] Merge pull request #237 from alibaba-damo-academy/dev_zc
---
funasr/bin/eend_ola_inference.py | 20 ++++++++++++++++++--
1 files changed, 18 insertions(+), 2 deletions(-)
diff --git a/funasr/bin/eend_ola_inference.py b/funasr/bin/eend_ola_inference.py
index 1a47c92..0483278 100755
--- a/funasr/bin/eend_ola_inference.py
+++ b/funasr/bin/eend_ola_inference.py
@@ -16,6 +16,7 @@
import numpy as np
import torch
+from scipy.signal import medfilt
from typeguard import check_argument_types
from funasr.models.frontend.wav_frontend import WavFrontendMel23
@@ -26,6 +27,7 @@
from funasr.utils.types import str2bool
from funasr.utils.types import str2triple_str
from funasr.utils.types import str_or_none
+
class Speech2Diarization:
"""Speech2Diarlization class
@@ -234,9 +236,23 @@
# batch = {k: v[0] for k, v in batch.items() if not k.endswith("_lengths")}
results = speech2diar(**batch)
+
+ # post process
+ a = results[0][0].cpu().numpy()
+ a = medfilt(a, (11, 1))
+ rst = []
+ for spkid, frames in enumerate(a.T):
+ frames = np.pad(frames, (1, 1), 'constant')
+ changes, = np.where(np.diff(frames, axis=0) != 0)
+ fmt = "SPEAKER {:s} 1 {:7.2f} {:7.2f} <NA> <NA> {:s} <NA>"
+ for s, e in zip(changes[::2], changes[1::2]):
+ st = s / 10.
+ dur = (e - s) / 10.
+ rst.append(fmt.format(keys[0], st, dur, "{}_{}".format(keys[0], str(spkid))))
+
# Only supporting batch_size==1
- key, value = keys[0], output_results_str(results, keys[0])
- item = {"key": key, "value": value}
+ value = "\n".join(rst)
+ item = {"key": keys[0], "value": value}
result_list.append(item)
if output_path is not None:
output_writer.write(value)
--
Gitblit v1.9.1