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

funasr1.0 streaming

Browse Source
This commit is contained in:
游雁 2024-01-12 13:29:37 +08:00
parent bafd056c28
commit 38524b21d9
2 changed files with 6 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
examples/industrial_data_pretraining/fsmn_vad_streaming/demo.py
View File

@ -26,9 +26,10 @@ chunk_stride = int(chunk_size * 16000 / 1000)
cache = {} cache = {}
for i in range(int(len((speech)-1)/chunk_stride+1)): total_chunk_num = int(len((speech)-1)/chunk_stride+1)
for i in range(total_chunk_num):
speech_chunk = speech[i*chunk_stride:(i+1)*chunk_stride] speech_chunk = speech[i*chunk_stride:(i+1)*chunk_stride]
is_final = i == int(len((speech)-1)/chunk_stride+1) - 1 is_final = i == total_chunk_num - 1
res = model(input=speech_chunk, res = model(input=speech_chunk,
cache=cache, cache=cache,
is_final=is_final, is_final=is_final,

6
examples/industrial_data_pretraining/paraformer_streaming/demo.py
View File

@ -28,10 +28,10 @@ speech, sample_rate = soundfile.read(wav_file)
chunk_stride = chunk_size[1] * 960 # 600ms、480ms chunk_stride = chunk_size[1] * 960 # 600ms、480ms
cache = {} cache = {}
total_chunk_num = int(len((speech)-1)/chunk_stride+1)
for i in range(int(len((speech)-1)/chunk_stride+1)): for i in range(total_chunk_num):
speech_chunk = speech[i*chunk_stride:(i+1)*chunk_stride] speech_chunk = speech[i*chunk_stride:(i+1)*chunk_stride]
is_final = i == int(len((speech)-1)/chunk_stride+1) - 1 is_final = i == total_chunk_num - 1
res = model(input=speech_chunk, res = model(input=speech_chunk,
cache=cache, cache=cache,
is_final=is_final, is_final=is_final,