Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.
Python asraudiochineseemotion-recognitionfunasrmcp-servermultilingual-asropenai-compatible-apiparaformerpunctuationpytorchreal-time-asrspeaker-diarizationspeech-recognitionspeech-to-textstreaming-asrtranscriptionvllmvoice-activity-detectionwhisper-alternative
docs: add detailed method docstrings to emotion2vec, eres2net, bicif_paraformer
游雁44dc6554fe57
diff --git a/funasr/models/eres2net/model.py b/funasr/models/eres2net/model.pyindex ebf624ecc..9969dd085 100644--- a/funasr/models/eres2net/model.py+++ b/funasr/models/eres2net/model.py@@ -19,6 +19,17 @@ from funasr.models.eres2net.eres2netv2 import ERes2NetV2@tables.register("model_classes", "ERes2NetV2")@tables.register("model_classes", "iic/speech_eres2netv2_sv_zh-cn_16k-common")class ERes2NetV2SV(torch.nn.Module):+ """ERes2NetV2: Enhanced Res2Net v2 for Speaker Verification.++ Improved speaker embedding model based on Res2Net architecture with+ multi-scale feature aggregation. Provides 192-dim speaker embeddings+ for speaker verification and diarization.++ Better than CAM++ for short-duration audio (< 3s) speaker feature extraction.++ Output: {"spk_embedding": Tensor of shape (1, 192)}+ """+def __init__(self,feat_dim=80,