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
add default emo and event target for sensevoice
北念bd352983c639
diff --git a/funasr/datasets/sense_voice_datasets/datasets.py b/funasr/datasets/sense_voice_datasets/datasets.pyindex 20232cc92..2e0266ef1 100644--- a/funasr/datasets/sense_voice_datasets/datasets.py+++ b/funasr/datasets/sense_voice_datasets/datasets.py@@ -325,8 +325,8 @@ class SenseVoiceCTCDataset(torch.utils.data.Dataset):asr_target = item["target"]if self.preprocessor_text:asr_target = self.preprocessor_text(asr_target)- emo_target = item["emo_target"]- event_target = item["event_target"]+ emo_target = item.get("emo_target", "<|NEUTRAL|>")+ event_target = item.get("event_target", "<|Speech|>")text_language = item.get("text_language", "<|zh|>")punc_itn_bottom = item.get("with_or_wo_itn", "<|woitn|>")