From b15db52e4e67da8a133a67e8ffa415386de48b40 Mon Sep 17 00:00:00 2001
From: zhuyunfeng <10596244@qq.com>
Date: 星期二, 09 五月 2023 23:03:15 +0800
Subject: [PATCH] Add contributor
---
funasr/bin/asr_inference_paraformer.py | 13 +++++++++----
1 files changed, 9 insertions(+), 4 deletions(-)
diff --git a/funasr/bin/asr_inference_paraformer.py b/funasr/bin/asr_inference_paraformer.py
index 2eeffcd..5335860 100644
--- a/funasr/bin/asr_inference_paraformer.py
+++ b/funasr/bin/asr_inference_paraformer.py
@@ -41,6 +41,7 @@
from funasr.utils import asr_utils, wav_utils, postprocess_utils
from funasr.models.frontend.wav_frontend import WavFrontend
from funasr.models.e2e_asr_paraformer import BiCifParaformer, ContextualParaformer
+from funasr.models.e2e_asr_contextual_paraformer import NeatContextualParaformer
from funasr.export.models.e2e_asr_paraformer import Paraformer as Paraformer_export
from funasr.utils.timestamp_tools import ts_prediction_lfr6_standard
from funasr.bin.tp_inference import SpeechText2Timestamp
@@ -236,7 +237,7 @@
pre_token_length = pre_token_length.round().long()
if torch.max(pre_token_length) < 1:
return []
- if not isinstance(self.asr_model, ContextualParaformer):
+ if not isinstance(self.asr_model, ContextualParaformer) and not isinstance(self.asr_model, NeatContextualParaformer):
if self.hotword_list:
logging.warning("Hotword is given but asr model is not a ContextualParaformer.")
decoder_outs = self.asr_model.cal_decoder_with_predictor(enc, enc_len, pre_acoustic_embeds, pre_token_length)
@@ -612,7 +613,9 @@
**kwargs,
):
assert check_argument_types()
-
+ ncpu = kwargs.get("ncpu", 1)
+ torch.set_num_threads(ncpu)
+
if word_lm_train_config is not None:
raise NotImplementedError("Word LM is not implemented")
if ngpu > 1:
@@ -629,7 +632,9 @@
export_mode = param_dict.get("export_mode", False)
else:
hotword_list_or_file = None
-
+
+ if kwargs.get("device", None) == "cpu":
+ ngpu = 0
if ngpu >= 1 and torch.cuda.is_available():
device = "cuda"
else:
@@ -797,7 +802,7 @@
finish_count += 1
# asr_utils.print_progress(finish_count / file_count)
if writer is not None:
- ibest_writer["text"][key] = text_postprocessed
+ ibest_writer["text"][key] = " ".join(word_lists)
logging.info("decoding, utt: {}, predictions: {}".format(key, text))
rtf_avg = "decoding, feature length total: {}, forward_time total: {:.4f}, rtf avg: {:.4f}".format(length_total, forward_time_total, 100 * forward_time_total / (length_total * lfr_factor))
--
Gitblit v1.9.1