34 lines
930 B
Python
34 lines
930 B
Python
from funasr import AutoModel
|
|
|
|
chunk_size = 200 # ms
|
|
model = AutoModel(
|
|
model="fsmn-vad",
|
|
model_revision="v2.0.4",
|
|
disable_update=True
|
|
)
|
|
|
|
import soundfile
|
|
|
|
wav_file = "tests/vad_example.wav"
|
|
speech, sample_rate = soundfile.read(wav_file)
|
|
chunk_stride = int(chunk_size * sample_rate / 1000)
|
|
|
|
cache = {}
|
|
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]
|
|
is_final = i == total_chunk_num - 1
|
|
res = model.generate(
|
|
input=speech_chunk,
|
|
cache=cache,
|
|
is_final=is_final,
|
|
chunk_size=chunk_size,
|
|
disable_pbar=True
|
|
)
|
|
if len(res[0]["value"]):
|
|
print(res)
|
|
|
|
print(f"len(speech): {len(speech)}")
|
|
print(f"len(speech_chunk): {len(speech_chunk)}")
|
|
print(f"total_chunk_num: {total_chunk_num}")
|
|
print(f"generateconfig: chunk_size: {chunk_size}, chunk_stride: {chunk_stride}") |