| | |
|---|
| | | 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, |
|---|
| | |
|---|
| | | |
|---|
| | | # 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() |
|---|
| | | if isinstance(key[0], (list, tuple)): |
|---|
