speech_recognition/FunASR
1
0
Fork 0
mirror of https://github.com/modelscope/FunASR synced 2025-09-15 14:48:36 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

vad conf

Browse Source
This commit is contained in:
游雁 2024-03-19 12:04:50 +08:00
parent 60a7d39f39
commit d29f201e32
5 changed files with 6 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
examples/industrial_data_pretraining/emotion2vec/demo.py
View File

@ -9,7 +9,7 @@ from funasr import AutoModel
model = AutoModel(model="iic/emotion2vec_base_finetuned", model_revision="v2.0.4",
# vad_model="iic/speech_fsmn_vad_zh-cn-16k-common-pytorch",
# vad_model_revision="v2.0.4",
# vad_kwargs={"max_single_segment_time": 10},
# vad_kwargs={"max_single_segment_time": 1000},
)
wav_file = f"{model.model_path}/example/test.wav"

2
examples/industrial_data_pretraining/paraformer/demo.py
View File

@ -9,7 +9,7 @@ model = AutoModel(model="iic/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-
model_revision="v2.0.4",
vad_model="iic/speech_fsmn_vad_zh-cn-16k-common-pytorch",
vad_model_revision="v2.0.4",
vad_kwargs={"max_single_segment_time": 60},
vad_kwargs={"max_single_segment_time": 60000},
punc_model="iic/punc_ct-transformer_zh-cn-common-vocab272727-pytorch",
punc_model_revision="v2.0.4",
# spk_model="iic/speech_campplus_sv_zh-cn_16k-common",

2
examples/industrial_data_pretraining/whisper/demo.py
View File

@ -10,7 +10,7 @@ from funasr import AutoModel
model = AutoModel(model="iic/Whisper-large-v3",
model_revision="v2.0.5",
vad_model="iic/speech_fsmn_vad_zh-cn-16k-common-pytorch",
vad_kwargs={"max_single_segment_time": 30},
vad_kwargs={"max_single_segment_time": 30000},
)
res = model.generate(

2
examples/industrial_data_pretraining/whisper/demo_from_openai.py
View File

@ -12,7 +12,7 @@ from funasr import AutoModel
# model = AutoModel(model="Whisper-large-v2", hub="openai")
model = AutoModel(model="Whisper-large-v3",
vad_model="iic/speech_fsmn_vad_zh-cn-16k-common-pytorch",
vad_kwargs={"max_single_segment_time": 30},
vad_kwargs={"max_single_segment_time": 30000},
hub="openai",
)

3
funasr/auto/auto_model.py
View File

@ -312,7 +312,8 @@ class AutoModel:
key = res[i]["key"]
vadsegments = res[i]["value"]
input_i = data_list[i]
speech = load_audio_text_image_video(input_i, fs=kwargs["frontend"].fs, audio_fs=kwargs.get("fs", 16000))
fs = kwargs["frontend"].fs if hasattr(kwargs["frontend"], "fs") else 16000
speech = load_audio_text_image_video(input_i, fs=fs, audio_fs=kwargs.get("fs", 16000))
speech_lengths = len(speech)
n = len(vadsegments)
data_with_index = [(vadsegments[i], i) for i in range(n)]