bugfix memory leaky

游雁

2024-09-25 fc547e14e818772811c3dccd9bb09e45e35df168

 funasr/models/sense_voice/model.py

@@ -196,13 +196,13 @@
                "inf"
            )  # float(numpy.finfo(torch.tensor(0, dtype=scores.dtype).numpy().dtype).min)
            scores = scores.masked_fill(mask, min_value)
            self.attn = torch.softmax(scores, dim=-1).masked_fill(
            attn = torch.softmax(scores, dim=-1).masked_fill(
                mask, 0.0
            )  # (batch, head, time1, time2)
        else:
            self.attn = torch.softmax(scores, dim=-1)  # (batch, head, time1, time2)
            attn = torch.softmax(scores, dim=-1)  # (batch, head, time1, time2)

        p_attn = self.dropout(self.attn)
        p_attn = self.dropout(attn)
        x = torch.matmul(p_attn, value)  # (batch, head, time1, d_k)
        x = (
            x.transpose(1, 2).contiguous().view(n_batch, -1, self.h * self.d_k)
@@ -644,7 +644,13 @@
        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.emo_dict = {
            "unk": 25009,
            "happy": 25001,
            "sad": 25002,
            "angry": 25003,
            "neutral": 25004,
        }

        self.criterion_att = LabelSmoothingLoss(
            size=self.vocab_size,
@@ -874,7 +880,7 @@
        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()
        if isinstance(key[0], (list, tuple)):