mirror of
https://github.com/snakers4/silero-vad.git
synced 2026-02-04 17:39:22 +08:00
fx
This commit is contained in:
@@ -27,6 +27,7 @@
|
||||
"start_time": "2020-12-15T14:00:09.512876Z"
|
||||
},
|
||||
"cellView": "form",
|
||||
"collapsed": true,
|
||||
"id": "rllMjjsekbjt"
|
||||
},
|
||||
"outputs": [],
|
||||
@@ -41,7 +42,7 @@
|
||||
"torch.set_num_threads(1)\n",
|
||||
"\n",
|
||||
"from IPython.display import Audio\n",
|
||||
"\n",
|
||||
"from pprint import pprint\n",
|
||||
"\n",
|
||||
"model, utils = torch.hub.load(repo_or_dir='snakers4/silero-vad',\n",
|
||||
" model='silero_vad',\n",
|
||||
@@ -63,7 +64,7 @@
|
||||
"id": "fXbbaUO3jsrw"
|
||||
},
|
||||
"source": [
|
||||
"## Full audio"
|
||||
"## Full Audio"
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -82,7 +83,7 @@
|
||||
"# get speech timestamps from full audio file\n",
|
||||
"speech_timestamps = get_speech_ts(wav, model,\n",
|
||||
" num_steps=4)\n",
|
||||
"print(speech_timestamps)"
|
||||
"pprint(speech_timestamps)"
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -170,7 +171,7 @@
|
||||
"source": [
|
||||
"for batch in state_generator(model, audios_for_stream, audios_in_stream=2): # 2 audio stream\n",
|
||||
" if batch:\n",
|
||||
" print(batch)"
|
||||
" pprint(batch)"
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -207,6 +208,7 @@
|
||||
"\n",
|
||||
"import glob\n",
|
||||
"import onnxruntime\n",
|
||||
"from pprint import pprint\n",
|
||||
"\n",
|
||||
"from IPython.display import Audio\n",
|
||||
"\n",
|
||||
@@ -240,7 +242,7 @@
|
||||
"id": "5JHErdB7jsr0"
|
||||
},
|
||||
"source": [
|
||||
"## Full audio"
|
||||
"## Full Audio"
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -260,7 +262,7 @@
|
||||
"\n",
|
||||
"# get speech timestamps from full audio file\n",
|
||||
"speech_timestamps = get_speech_ts(wav, model, num_steps=4, run_function=validate_onnx) \n",
|
||||
"print(speech_timestamps)"
|
||||
"pprint(speech_timestamps)"
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -286,7 +288,7 @@
|
||||
"id": "Rio9W50gjsr1"
|
||||
},
|
||||
"source": [
|
||||
"## Single audio stream"
|
||||
"## Single Audio Stream"
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -319,7 +321,7 @@
|
||||
"source": [
|
||||
"for batch in single_audio_stream(model, wav, run_function=validate_onnx):\n",
|
||||
" if batch:\n",
|
||||
" print(batch)"
|
||||
" pprint(batch)"
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -328,7 +330,7 @@
|
||||
"id": "WNZ42u0ajsr1"
|
||||
},
|
||||
"source": [
|
||||
"## Multiple audio stream"
|
||||
"## Multiple Audio Streams"
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -345,7 +347,7 @@
|
||||
"source": [
|
||||
"model = init_onnx_model(f'{files_dir}/model.onnx')\n",
|
||||
"audios_for_stream = glob.glob(f'{files_dir}/*.wav')\n",
|
||||
"print(len(audios_for_stream)) # total 4 audios"
|
||||
"pprint(len(audios_for_stream)) # total 4 audios"
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -362,7 +364,7 @@
|
||||
"source": [
|
||||
"for batch in state_generator(model, audios_for_stream, audios_in_stream=2, run_function=validate_onnx): # 2 audio stream\n",
|
||||
" if batch:\n",
|
||||
" print(batch)"
|
||||
" pprint(batch)"
|
||||
]
|
||||
}
|
||||
],
|
||||
|
||||
Reference in New Issue
Block a user