mirror of
https://github.com/modelscope/FunASR.git
synced 2026-10-12 02:19:18 +00:00
游雁
106cbb69a3
Integrates ERes2NetV2 from 3D-Speaker into FunASR as a speaker
verification/diarization model. Can be used standalone or as spk_model
combined with VAD + ASR for speaker-attributed transcription.
Usage (standalone speaker embedding):
model = AutoModel(model="iic/speech_eres2netv2_sv_zh-cn_16k-common")
res = model.generate(input="audio.wav")
embedding = res[0]["spk_embedding"] # shape: [1, 192]
Usage (with ASR + speaker diarization):
model = AutoModel(
model="paraformer-zh",
vad_model="fsmn-vad",
spk_model="iic/speech_eres2netv2_sv_zh-cn_16k-common",
)
res = model.generate(input="audio.wav")
Tested end-to-end: ModelScope download + embedding extraction verified.
New files:
- funasr/models/eres2net/eres2netv2.py (network architecture)
- funasr/models/eres2net/model.py (FunASR wrapper with inference)
- tests_models/test_eres2netv2.py
- examples/industrial_data_pretraining/eres2netv2_sv/demo.py
- examples/industrial_data_pretraining/eres2netv2_sv/demo_sv.py
68 lines
2.2 KiB
Python
68 lines
2.2 KiB
Python
#!/usr/bin/env python3
|
|
"""Test ERes2NetV2: speaker verification/diarization with ASR"""
|
|
import sys
|
|
import time
|
|
|
|
|
|
def main():
|
|
from funasr import AutoModel
|
|
|
|
url_zh = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav"
|
|
|
|
# Test 1: ERes2NetV2 as spk_model combined with VAD + ASR
|
|
print("[ERes2NetV2] Loading model with VAD + ASR + SPK...")
|
|
t0 = time.time()
|
|
model = AutoModel(
|
|
model="iic/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch",
|
|
vad_model="iic/speech_fsmn_vad_zh-cn-16k-common-pytorch",
|
|
vad_kwargs={"max_single_segment_time": 60000},
|
|
spk_model="iic/speech_eres2netv2_sv_zh-cn_16k-common",
|
|
device="cuda:0",
|
|
disable_update=True,
|
|
)
|
|
print("[ERes2NetV2] Model loaded in %.1fs" % (time.time() - t0))
|
|
|
|
# Test with speaker diarization
|
|
print("[ERes2NetV2] Running inference with speaker diarization...")
|
|
t0 = time.time()
|
|
res = model.generate(
|
|
input=url_zh,
|
|
batch_size_s=300,
|
|
)
|
|
print("[ERes2NetV2] Inference done in %.1fs" % (time.time() - t0))
|
|
|
|
if res and len(res) > 0 and "text" in res[0]:
|
|
print("[ERes2NetV2] Result: %s" % res[0]["text"])
|
|
if "spk" in res[0]:
|
|
print("[ERes2NetV2] Speaker: %s" % res[0]["spk"])
|
|
print("[ERes2NetV2] Test 1 PASSED")
|
|
else:
|
|
print("[ERes2NetV2] Test 1 FAILED - no text in result")
|
|
return 1
|
|
|
|
# Test 2: ERes2NetV2 standalone speaker embedding
|
|
print("[ERes2NetV2] Test 2: Standalone speaker embedding...")
|
|
t0 = time.time()
|
|
spk_model = AutoModel(
|
|
model="iic/speech_eres2netv2_sv_zh-cn_16k-common",
|
|
device="cuda:0",
|
|
disable_update=True,
|
|
)
|
|
res = spk_model.generate(input=url_zh)
|
|
print("[ERes2NetV2] Embedding done in %.1fs" % (time.time() - t0))
|
|
|
|
if res and len(res) > 0 and "spk_embedding" in res[0]:
|
|
emb = res[0]["spk_embedding"]
|
|
print("[ERes2NetV2] Embedding shape: %s" % str(emb.shape))
|
|
print("[ERes2NetV2] Test 2 PASSED")
|
|
else:
|
|
print("[ERes2NetV2] Test 2 FAILED - no spk_embedding in result")
|
|
return 1
|
|
|
|
print("[ERes2NetV2] All tests PASSED")
|
|
return 0
|
|
|
|
|
|
if __name__ == "__main__":
|
|
sys.exit(main())
|