From 94a4dbba3d1f766001f9b40559efe1f76f9c108d Mon Sep 17 00:00:00 2001
From: 嘉渊 <wangjiaming.wjm@alibaba-inc.com>
Date: 星期二, 16 五月 2023 18:37:49 +0800
Subject: [PATCH] Merge branch 'dev_infer' of https://github.com/alibaba/FunASR into dev_infer
---
egs_modelscope/tp/speech_timestamp_prediction-v1-16k-offline/demo.py | 1 +
egs_modelscope/tp/TEMPLATE/infer.py | 3 ++-
egs_modelscope/punctuation/punc_ct-transformer_zh-cn-common-vocab272727-pytorch/demo.py | 19 +++++++++----------
funasr/bin/asr_inference_launch.py | 6 ++++++
egs_modelscope/punctuation/punc_ct-transformer_zh-cn-common-vadrealtime-vocab272727/demo.py | 7 +++----
5 files changed, 21 insertions(+), 15 deletions(-)
diff --git a/egs_modelscope/punctuation/punc_ct-transformer_zh-cn-common-vadrealtime-vocab272727/demo.py b/egs_modelscope/punctuation/punc_ct-transformer_zh-cn-common-vadrealtime-vocab272727/demo.py
index a6629cd..cf115b1 100644
--- a/egs_modelscope/punctuation/punc_ct-transformer_zh-cn-common-vadrealtime-vocab272727/demo.py
+++ b/egs_modelscope/punctuation/punc_ct-transformer_zh-cn-common-vadrealtime-vocab272727/demo.py
@@ -1,7 +1,3 @@
-
-##################text浜岃繘鍒舵暟鎹�#####################
-inputs = "璺ㄥ娌虫祦鏄吇鑲叉部宀竱浜烘皯鐨勭敓鍛戒箣婧愰暱鏈熶互鏉ヤ负甯姪涓嬫父鍦板尯闃茬伨鍑忕伨涓柟鎶�鏈汉鍛榺鍦ㄤ笂娓稿湴鍖烘瀬涓烘伓鍔ｇ殑鑷劧鏉′欢涓嬪厠鏈嶅法澶у洶闅剧敋鑷冲啋鐫�鐢熷懡鍗遍櫓|鍚戝嵃鏂规彁渚涙睕鏈熸按鏂囪祫鏂欏鐞嗙揣鎬ヤ簨浠朵腑鏂归噸瑙嗗嵃鏂瑰湪璺ㄥ娌虫祦闂涓婄殑鍏冲垏|鎰挎剰杩涗竴姝ュ畬鍠勫弻鏂硅仈鍚堝伐浣滄満鍒秥鍑℃槸|涓柟鑳藉仛鐨勬垜浠瑋閮戒細鍘诲仛鑰屼笖浼氬仛寰楁洿濂芥垜璇峰嵃搴︽湅鍙嬩滑鏀惧績涓浗鍦ㄤ笂娓哥殑|浠讳綍寮�鍙戝埄鐢ㄩ兘浼氱粡杩囩瀛瑙勫垝鍜岃璇佸吋椤句笂涓嬫父鐨勫埄鐩�"
-
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks
from modelscope.utils.logger import get_logger
@@ -16,6 +12,9 @@
output_dir="./tmp/"
)
+##################text浜岃繘鍒舵暟鎹�#####################
+inputs = "璺ㄥ娌虫祦鏄吇鑲叉部宀竱浜烘皯鐨勭敓鍛戒箣婧愰暱鏈熶互鏉ヤ负甯姪涓嬫父鍦板尯闃茬伨鍑忕伨涓柟鎶�鏈汉鍛榺鍦ㄤ笂娓稿湴鍖烘瀬涓烘伓鍔ｇ殑鑷劧鏉′欢涓嬪厠鏈嶅法澶у洶闅剧敋鑷冲啋鐫�鐢熷懡鍗遍櫓|鍚戝嵃鏂规彁渚涙睕鏈熸按鏂囪祫鏂欏鐞嗙揣鎬ヤ簨浠朵腑鏂归噸瑙嗗嵃鏂瑰湪璺ㄥ娌虫祦闂涓婄殑鍏冲垏|鎰挎剰杩涗竴姝ュ畬鍠勫弻鏂硅仈鍚堝伐浣滄満鍒秥鍑℃槸|涓柟鑳藉仛鐨勬垜浠瑋閮戒細鍘诲仛鑰屼笖浼氬仛寰楁洿濂芥垜璇峰嵃搴︽湅鍙嬩滑鏀惧績涓浗鍦ㄤ笂娓哥殑|浠讳綍寮�鍙戝埄鐢ㄩ兘浼氱粡杩囩瀛瑙勫垝鍜岃璇佸吋椤句笂涓嬫父鐨勫埄鐩�"
+
vads = inputs.split("|")
rec_result_all="outputs:"
param_dict = {"cache": []}
diff --git a/egs_modelscope/punctuation/punc_ct-transformer_zh-cn-common-vocab272727-pytorch/demo.py b/egs_modelscope/punctuation/punc_ct-transformer_zh-cn-common-vocab272727-pytorch/demo.py
index 45b5e33..7383a58 100644
--- a/egs_modelscope/punctuation/punc_ct-transformer_zh-cn-common-vocab272727-pytorch/demo.py
+++ b/egs_modelscope/punctuation/punc_ct-transformer_zh-cn-common-vocab272727-pytorch/demo.py
@@ -1,14 +1,4 @@
-##################text.scp###################
-# inputs = "./egs_modelscope/punctuation/punc_ct-transformer_zh-cn-common-vocab272727-pytorch/data/punc_example.txt"
-
-##################text#####################
-#inputs = "鎴戜滑閮芥槸鏈ㄥご浜轰笉浼氳璇濅笉浼氬姩"
-
-##################text file url#######################
-inputs = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_text/punc_example.txt"
-
-
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks
@@ -19,5 +9,14 @@
output_dir="./tmp/"
)
+##################text.scp###################
+# inputs = "./egs_modelscope/punctuation/punc_ct-transformer_zh-cn-common-vocab272727-pytorch/data/punc_example.txt"
+
+##################text#####################
+#inputs = "鎴戜滑閮芥槸鏈ㄥご浜轰笉浼氳璇濅笉浼氬姩"
+
+##################text file url#######################
+inputs = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_text/punc_example.txt"
+
rec_result = inference_pipeline(text_in=inputs)
print(rec_result)
diff --git a/egs_modelscope/tp/TEMPLATE/infer.py b/egs_modelscope/tp/TEMPLATE/infer.py
index 6a7e496..732c984 100644
--- a/egs_modelscope/tp/TEMPLATE/infer.py
+++ b/egs_modelscope/tp/TEMPLATE/infer.py
@@ -8,6 +8,7 @@
inference_pipeline = pipeline(
task=Tasks.speech_timestamp,
model=args.model,
+ model_revision='v1.1.0',
output_dir=args.output_dir,
batch_size=args.batch_size,
)
@@ -21,7 +22,7 @@
parser.add_argument('--model', type=str, default="damo/speech_timestamp_prediction-v1-16k-offline")
parser.add_argument('--audio_in', type=str, default="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_timestamps.wav")
parser.add_argument('--text_in', type=str, default="涓� 涓� 涓� 澶� 骞� 娲� 鍥� 瀹� 涓� 浠� 涔� 璺� 鍒� 瑗� 澶� 骞� 娲� 鏉� 浜� 鍛�")
- parser.add_argument('--output_dir', type=str, default="./results/")
+ parser.add_argument('--output_dir', type=str, default=None)
parser.add_argument('--batch_size', type=int, default=1)
parser.add_argument('--gpuid', type=str, default="0")
args = parser.parse_args()
diff --git a/egs_modelscope/tp/speech_timestamp_prediction-v1-16k-offline/demo.py b/egs_modelscope/tp/speech_timestamp_prediction-v1-16k-offline/demo.py
index bcc5128..3116f6d 100644
--- a/egs_modelscope/tp/speech_timestamp_prediction-v1-16k-offline/demo.py
+++ b/egs_modelscope/tp/speech_timestamp_prediction-v1-16k-offline/demo.py
@@ -4,6 +4,7 @@
inference_pipeline = pipeline(
task=Tasks.speech_timestamp,
model='damo/speech_timestamp_prediction-v1-16k-offline',
+ model_revision='v1.1.0',
output_dir=None)
rec_result = inference_pipeline(
diff --git a/funasr/bin/asr_inference_launch.py b/funasr/bin/asr_inference_launch.py
index 4a55caa..f9b8571 100644
--- a/funasr/bin/asr_inference_launch.py
+++ b/funasr/bin/asr_inference_launch.py
@@ -1526,6 +1526,12 @@
action="append",
)
group.add_argument("--key_file", type=str_or_none)
+ parser.add_argument(
+ "--hotword",
+ type=str_or_none,
+ default=None,
+ help="hotword file path or hotwords seperated by space"
+ )
group.add_argument("--allow_variable_data_keys", type=str2bool, default=False)
group.add_argument(
"--mc",
--
Gitblit v1.9.1