FunASR

mirror of https://github.com/modelscope/FunASR.git synced 2026-10-12 02:19:18 +00:00

Files

T

游雁 106cbb69a3 feat: add ERes2NetV2 speaker model with full AutoModel integration

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

2026-05-20 05:27:53 +00:00

auto

fix: device fallback handles cuda:N format correctly

2026-05-19 17:28:19 +00:00

bin

fix: fix undefined variable in FSDP auto_wrap_policy (train.py)

2026-05-19 17:52:57 +00:00

datasets

fix: resolve multiple issues (#2689 , #2720 , #2755 , #2780 )

2026-05-19 14:14:10 +00:00

download

bugfix