From 0ee4565c8ec3deffde8362370aee306ae7029ebb Mon Sep 17 00:00:00 2001
From: shixian.shi <shixian.shi@alibaba-inc.com>
Date: 星期一, 22 一月 2024 18:44:07 +0800
Subject: [PATCH] update raw_text
---
funasr/auto/auto_model.py | 15 ++++++++-------
1 files changed, 8 insertions(+), 7 deletions(-)
diff --git a/funasr/auto/auto_model.py b/funasr/auto/auto_model.py
index ca6189d..1c7288e 100644
--- a/funasr/auto/auto_model.py
+++ b/funasr/auto/auto_model.py
@@ -6,6 +6,7 @@
import string
import logging
import os.path
+import numpy as np
from tqdm import tqdm
from omegaconf import DictConfig, OmegaConf, ListConfig
@@ -96,7 +97,7 @@
vad_kwargs = kwargs.get("vad_model_revision", None)
if vad_model is not None:
logging.info("Building VAD model.")
- vad_kwargs = {"model": vad_model, "model_revision": vad_kwargs}
+ vad_kwargs = {"model": vad_model, "model_revision": vad_kwargs, "device": kwargs["device"]}
vad_model, vad_kwargs = self.build_model(**vad_kwargs)
# if punc_model is not None, build punc model else None
@@ -104,7 +105,7 @@
punc_kwargs = kwargs.get("punc_model_revision", None)
if punc_model is not None:
logging.info("Building punc model.")
- punc_kwargs = {"model": punc_model, "model_revision": punc_kwargs}
+ punc_kwargs = {"model": punc_model, "model_revision": punc_kwargs, "device": kwargs["device"]}
punc_model, punc_kwargs = self.build_model(**punc_kwargs)
# if spk_model is not None, build spk model else None
@@ -112,9 +113,9 @@
spk_kwargs = kwargs.get("spk_model_revision", None)
if spk_model is not None:
logging.info("Building SPK model.")
- spk_kwargs = {"model": spk_model, "model_revision": spk_kwargs}
+ spk_kwargs = {"model": spk_model, "model_revision": spk_kwargs, "device": kwargs["device"]}
spk_model, spk_kwargs = self.build_model(**spk_kwargs)
- self.cb_model = ClusterBackend()
+ self.cb_model = ClusterBackend().to(kwargs["device"])
spk_mode = kwargs.get("spk_mode", 'punc_segment')
if spk_mode not in ["default", "vad_segment", "punc_segment"]:
logging.error("spk_mode should be one of default, vad_segment and punc_segment.")
@@ -334,7 +335,7 @@
for _b in range(len(speech_j)):
vad_segments = [[sorted_data[beg_idx:end_idx][_b][0][0]/1000.0,
sorted_data[beg_idx:end_idx][_b][0][1]/1000.0,
- speech_j[_b]]]
+ np.array(speech_j[_b])]]
segments = sv_chunk(vad_segments)
all_segments.extend(segments)
speech_b = [i[2] for i in segments]
@@ -397,7 +398,7 @@
if self.spk_model is not None:
all_segments = sorted(all_segments, key=lambda x: x[0])
spk_embedding = result['spk_embedding']
- labels = self.cb_model(spk_embedding, oracle_num=self.preset_spk_num)
+ labels = self.cb_model(spk_embedding.cpu(), oracle_num=self.preset_spk_num)
del result['spk_embedding']
sv_output = postprocess(all_segments, None, labels, spk_embedding.cpu())
if self.spk_mode == 'vad_segment':
@@ -405,7 +406,7 @@
for res, vadsegment in zip(restored_data, vadsegments):
sentence_list.append({"start": vadsegment[0],\
"end": vadsegment[1],
- "sentence": res['text'],
+ "sentence": res['raw_text'],
"timestamp": res['timestamp']})
else: # punc_segment
sentence_list = timestamp_sentence(punc_res[0]['punc_array'], \
--
Gitblit v1.9.1