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 class docstrings to qwen_audio and whisper models
游雁4b38833603ae
diff --git a/funasr/models/qwen_audio/model.py b/funasr/models/qwen_audio/model.pyindex f78d8914b..9c5947145 100644--- a/funasr/models/qwen_audio/model.py+++ b/funasr/models/qwen_audio/model.py@@ -102,6 +102,12 @@ class QwenAudioWarp(nn.Module):@tables.register("model_classes", "QwenAudioChat")@tables.register("model_classes", "QwenAudioChatWarp")class QwenAudioChatWarp(nn.Module):+ """QwenAudioChat: Qwen Audio Chat model wrapper.++ Interactive audio chat using the Qwen-Audio-Chat model.+ Supports multi-turn conversation about audio content.+ """+def __init__(self, *args, **kwargs):"""Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Modelsdiff --git a/funasr/models/whisper/model.py b/funasr/models/whisper/model.pyindex d2656dcce..a8f183b89 100644--- a/funasr/models/whisper/model.py+++ b/funasr/models/whisper/model.py@@ -31,6 +31,15 @@ from funasr.register import tables@tables.register("model_classes", "Whisper-large-v3-turbo")@tables.register("model_classes", "WhisperWarp")class WhisperWarp(nn.Module):+ """Whisper: OpenAI Whisper model integration.++ Wraps Whisper for multilingual speech recognition and translation+ within FunASR's AutoModel interface.++ Supports: whisper-tiny through whisper-large-v3-turbo.+ Output: {"key": str, "text": str}+ """+def __init__(self, *args, **kwargs):"""Initialize WhisperWarp.