Dev gzf exp (#1654)

zhifu gao

2024-04-24 861147c7308b91068ffa02724fdf74ee623a909e

 funasr/models/ct_transformer/model.py

@@ -17,6 +17,7 @@
from funasr.utils.load_utils import load_audio_text_image_video
from funasr.models.transformer.utils.nets_utils import make_pad_mask
from funasr.models.ct_transformer.utils import split_to_mini_sentence, split_words

try:
    import jieba
except:
@@ -37,6 +38,7 @@
    CT-Transformer: Controllable time-delay transformer for real-time punctuation prediction and disfluency detection
    https://arxiv.org/pdf/2003.01309.pdf
    """

    def __init__(
        self,
        encoder: str = None,
@@ -59,7 +61,6 @@
        if punc_weight is None:
            punc_weight = [1] * punc_size
        
        
        self.embed = torch.nn.Embedding(vocab_size, embed_unit)
        encoder_class = tables.encoder_classes.get(encoder)
        encoder = encoder_class(**encoder_conf)
@@ -76,8 +77,6 @@
        if kwargs.get("jieba_usr_dict", None) is not None:
            jieba.load_userdict(kwargs["jieba_usr_dict"])
            self.jieba_usr_dict = jieba
        
        

    def punc_forward(self, text: torch.Tensor, text_lengths: torch.Tensor, **kwargs):
        """Compute loss value from buffer sequences.
@@ -111,12 +110,16 @@

        """
        y = y.unsqueeze(0)
        h, _, cache = self.encoder.forward_one_step(self.embed(y), self._target_mask(y), cache=state)
        h, _, cache = self.encoder.forward_one_step(
            self.embed(y), self._target_mask(y), cache=state
        )
        h = self.decoder(h[:, -1])
        logp = h.log_softmax(dim=-1).squeeze(0)
        return logp, cache

    def batch_score(self, ys: torch.Tensor, states: List[Any], xs: torch.Tensor) -> Tuple[torch.Tensor, List[Any]]:
    def batch_score(
        self, ys: torch.Tensor, states: List[Any], xs: torch.Tensor
    ) -> Tuple[torch.Tensor, List[Any]]:
        """Score new token batch.

        Args:
@@ -138,10 +141,14 @@
            batch_state = None
        else:
            # transpose state of [batch, layer] into [layer, batch]
            batch_state = [torch.stack([states[b][i] for b in range(n_batch)]) for i in range(n_layers)]
            batch_state = [
                torch.stack([states[b][i] for b in range(n_batch)]) for i in range(n_layers)
            ]

        # batch decoding
        h, _, states = self.encoder.forward_one_step(self.embed(ys), self._target_mask(ys), cache=batch_state)
        h, _, states = self.encoder.forward_one_step(
            self.embed(ys), self._target_mask(ys), cache=batch_state
        )
        h = self.decoder(h[:, -1])
        logp = h.log_softmax(dim=-1)

@@ -190,15 +197,23 @@
        if self.training == False:
            _, indices = y.view(-1, y.shape[-1]).topk(1, dim=1)
            from sklearn.metrics import f1_score
            f1_score = f1_score(punc.view(-1).detach().cpu().numpy(),

            f1_score = f1_score(
                punc.view(-1).detach().cpu().numpy(),
                                indices.squeeze(-1).detach().cpu().numpy(),
                                average='micro')
                average="micro",
            )
            nll = torch.Tensor([f1_score]).repeat(text_lengths.sum())
            return nll, text_lengths
        else:
            self.punc_weight = self.punc_weight.to(punc.device)
            nll = F.cross_entropy(y.view(-1, y.shape[-1]), punc.view(-1), self.punc_weight, reduction="none",
                                  ignore_index=self.ignore_id)
            nll = F.cross_entropy(
                y.view(-1, y.shape[-1]),
                punc.view(-1),
                self.punc_weight,
                reduction="none",
                ignore_index=self.ignore_id,
            )
        # nll: (BxL,) -> (BxL,)
        if max_length is None:
            nll.masked_fill_(make_pad_mask(text_lengths).to(nll.device).view(-1), 0.0)
@@ -210,7 +225,6 @@
        # nll: (BxL,) -> (B, L)
        nll = nll.view(batch_size, -1)
        return nll, text_lengths


    def forward(
        self,
@@ -230,7 +244,8 @@
        loss, stats, weight = force_gatherable((loss, stats, ntokens), loss.device)
        return loss, stats, weight
    
    def inference(self,
    def inference(
        self,
                 data_in,
                 data_lengths=None,
                 key: list = None,
@@ -252,7 +267,7 @@
        mini_sentences_id = split_to_mini_sentence(tokens_int, split_size)
        assert len(mini_sentences) == len(mini_sentences_id)
        cache_sent = []
        cache_sent_id = torch.from_numpy(np.array([], dtype='int32'))
        cache_sent_id = torch.from_numpy(np.array([], dtype="int32"))
        new_mini_sentence = ""
        new_mini_sentence_punc = []
        cache_pop_trigger_limit = 200
@@ -266,7 +281,7 @@
            mini_sentence_id = np.concatenate((cache_sent_id, mini_sentence_id), axis=0)
            data = {
                "text": torch.unsqueeze(torch.from_numpy(mini_sentence_id), 0),
                "text_lengths": torch.from_numpy(np.array([len(mini_sentence_id)], dtype='int32')),
                "text_lengths": torch.from_numpy(np.array([len(mini_sentence_id)], dtype="int32")),
            }
            data = to_device(data, kwargs["device"])
            # y, _ = self.wrapped_model(**data)
@@ -282,13 +297,20 @@
                sentenceEnd = -1
                last_comma_index = -1
                for i in range(len(punctuations) - 2, 1, -1):
                    if self.punc_list[punctuations[i]] == "。" or self.punc_list[punctuations[i]] == "？":
                    if (
                        self.punc_list[punctuations[i]] == "。"
                        or self.punc_list[punctuations[i]] == "？"
                    ):
                        sentenceEnd = i
                        break
                    if last_comma_index < 0 and self.punc_list[punctuations[i]] == "，":
                        last_comma_index = i

                if sentenceEnd < 0 and len(mini_sentence) > cache_pop_trigger_limit and last_comma_index >= 0:
                if (
                    sentenceEnd < 0
                    and len(mini_sentence) > cache_pop_trigger_limit
                    and last_comma_index >= 0
                ):
                    # The sentence it too long, cut off at a comma.
                    sentenceEnd = last_comma_index
                    punctuations[sentenceEnd] = self.sentence_end_id
@@ -304,13 +326,20 @@
            new_mini_sentence_punc += [int(x) for x in punctuations_np]
            words_with_punc = []
            for i in range(len(mini_sentence)):
                if (i==0 or self.punc_list[punctuations[i-1]] == "。" or self.punc_list[punctuations[i-1]] == "？") and len(mini_sentence[i][0].encode()) == 1:
                if (
                    i == 0
                    or self.punc_list[punctuations[i - 1]] == "。"
                    or self.punc_list[punctuations[i - 1]] == "？"
                ) and len(mini_sentence[i][0].encode()) == 1:
                    mini_sentence[i] = mini_sentence[i].capitalize()
                if i == 0:
                    if len(mini_sentence[i][0].encode()) == 1:
                        mini_sentence[i] = " " + mini_sentence[i]
                if i > 0:
                    if len(mini_sentence[i][0].encode()) == 1 and len(mini_sentence[i - 1][0].encode()) == 1:
                    if (
                        len(mini_sentence[i][0].encode()) == 1
                        and len(mini_sentence[i - 1][0].encode()) == 1
                    ):
                        mini_sentence[i] = " " + mini_sentence[i]
                words_with_punc.append(mini_sentence[i])
                if self.punc_list[punctuations[i]] != "_":
@@ -330,18 +359,36 @@
            if mini_sentence_i == len(mini_sentences) - 1:
                if new_mini_sentence[-1] == "，" or new_mini_sentence[-1] == "、":
                    new_mini_sentence_out = new_mini_sentence[:-1] + "。"
                    new_mini_sentence_punc_out = new_mini_sentence_punc[:-1] + [self.sentence_end_id]
                    new_mini_sentence_punc_out = new_mini_sentence_punc[:-1] + [
                        self.sentence_end_id
                    ]
                elif new_mini_sentence[-1] == ",":
                    new_mini_sentence_out = new_mini_sentence[:-1] + "."
                    new_mini_sentence_punc_out = new_mini_sentence_punc[:-1] + [self.sentence_end_id]
                elif new_mini_sentence[-1] != "。" and new_mini_sentence[-1] != "？" and len(new_mini_sentence[-1].encode())!=1:
                    new_mini_sentence_punc_out = new_mini_sentence_punc[:-1] + [
                        self.sentence_end_id
                    ]
                elif (
                    new_mini_sentence[-1] != "。"
                    and new_mini_sentence[-1] != "？"
                    and len(new_mini_sentence[-1].encode()) != 1
                ):
                    new_mini_sentence_out = new_mini_sentence + "。"
                    new_mini_sentence_punc_out = new_mini_sentence_punc[:-1] + [self.sentence_end_id]
                    if len(punctuations): punctuations[-1] = 2
                elif new_mini_sentence[-1] != "." and new_mini_sentence[-1] != "?" and len(new_mini_sentence[-1].encode())==1:
                    new_mini_sentence_punc_out = new_mini_sentence_punc[:-1] + [
                        self.sentence_end_id
                    ]
                    if len(punctuations):
                        punctuations[-1] = 2
                elif (
                    new_mini_sentence[-1] != "."
                    and new_mini_sentence[-1] != "?"
                    and len(new_mini_sentence[-1].encode()) == 1
                ):
                    new_mini_sentence_out = new_mini_sentence + "."
                    new_mini_sentence_punc_out = new_mini_sentence_punc[:-1] + [self.sentence_end_id]
                    if len(punctuations): punctuations[-1] = 2
                    new_mini_sentence_punc_out = new_mini_sentence_punc[:-1] + [
                        self.sentence_end_id
                    ]
                    if len(punctuations):
                        punctuations[-1] = 2
            # keep a punctuations array for punc segment 
            if punc_array is None:
                punc_array = punctuations
@@ -355,7 +402,7 @@
            new_punc_array = copy.copy(punc_array).tolist()
            # for i, (token, punc_id) in enumerate(zip(tokens[::-1], punc_array.tolist()[::-1])):
            for i, token in enumerate(tokens[::-1]):
                if '\u0e00' <= token[0] <= '\u9fa5': # ignore en words
                if "\u0e00" <= token[0] <= "\u9fa5":  # ignore en words
                    if len(token) > 1:
                        num_append = len(token) - 1
                        ind_append = len_tokens - i - 1
@@ -370,7 +417,6 @@
    def export(self, **kwargs):
    
        from .export_meta import export_rebuild_model

        models = export_rebuild_model(model=self, **kwargs)
        return models