funasr/models/sense_voice/model.py
@@ -644,6 +644,7 @@ self.embed = torch.nn.Embedding( 7 + len(self.lid_dict) + len(self.textnorm_dict), input_size ) self.emo_dict = {"unk": 25009, "happy": 25001, "sad": 25002, "angry": 25003, "neutral": 25004} self.criterion_att = LabelSmoothingLoss( size=self.vocab_size, @@ -870,6 +871,8 @@ # c. Passed the encoder result and the beam search ctc_logits = self.ctc.log_softmax(encoder_out) if kwargs.get("ban_emo_unk", False): ctc_logits[:, :, self.emo_dict["unk"]] = -float("inf") results = [] b, n, d = encoder_out.size()
