Fix word pipleline (#749)

docs/source/change_log.md

@@ -16,7 +16,7 @@ Second internal release.
 * add palm2.0
 * add space model
 * add MPLUG model
-* add dialog_intent, dialog_modeling, dialog state tracking pipleline
+* add dialog_intent, dialog_modeling, dialog state tracking pipeline
 * add maskedlm model and fill_mask pipeline
 * add nli pipeline
 * add sentence similarity pipeline
@@ -28,7 +28,7 @@ Second internal release.
 
 #### Audio
 * add tts pipeline
-* add kws kwsbp pipline
+* add kws kwsbp pipeline
 * add linear aec pipeline
 * add ans pipeline
 

modelscope/models/multi_modal/clip/bert_tokenizer.py

@@ -157,7 +157,7 @@ def whitespace_tokenize(text):
 
 
 class FullTokenizer(object):
-    """Runs end-to-end tokenziation."""
+    """Runs end-to-end tokenization."""
 
     def __init__(self, vocab_file, do_lower_case=True):
         self.vocab = load_vocab(vocab_file)
@@ -185,7 +185,7 @@ class FullTokenizer(object):
 
         def clean_up_tokenization(out_string):
             """ Clean up a list of simple English tokenization artifacts
-            like spaces before punctuations and abreviated forms.
+            like spaces before punctuations and abbreviated forms.
             """
             out_string = (
                 out_string.replace(' .', '.').replace(' ?', '?').replace(
@@ -321,7 +321,7 @@ class BasicTokenizer(object):
 
 
 class WordpieceTokenizer(object):
-    """Runs WordPiece tokenziation."""
+    """Runs WordPiece tokenization."""
 
     def __init__(self, vocab, unk_token='[UNK]', max_input_chars_per_word=200):
         self.vocab = vocab
@@ -384,7 +384,7 @@ class WordpieceTokenizer(object):
 
 def _is_whitespace(char):
     """Checks whether `chars` is a whitespace character."""
-    # \t, \n, and \r are technically contorl characters but we treat them
+    # \t, \n, and \r are technically control characters but we treat them
     # as whitespace since they are generally considered as such.
     if char == ' ' or char == '\t' or char == '\n' or char == '\r':
         return True

modelscope/models/multi_modal/clip/configuration_bert.py

@@ -37,7 +37,7 @@ class BertConfig(object):
                 layer in the Transformer encoder.
             hidden_act: The non-linear activation function (function or string) in the
                 encoder and pooler. If string, "gelu", "relu", "swish" and "gelu_new" are supported.
-            hidden_dropout_prob: The dropout probabilitiy for all fully connected
+            hidden_dropout_prob: The dropout probability for all fully connected
                 layers in the embeddings, encoder, and pooler.
             attention_probs_dropout_prob: The dropout ratio for the attention
                 probabilities.

modelscope/models/multi_modal/clip/modeling_bert.py

@@ -485,7 +485,7 @@ class BertModel(BertPreTrainedModel):
                 head_mask = head_mask.unsqueeze(1).unsqueeze(-1).unsqueeze(
                     -1)  # We can specify head_mask for each layer
             head_mask = head_mask.to(dtype=next(self.parameters(
-            )).dtype)  # switch to fload if need + fp16 compatibility
+            )).dtype)  # switch to float if need + fp16 compatibility
         else:
             head_mask = [None] * self.config.num_hidden_layers
 

modelscope/models/multi_modal/diffusion/structbert.py

@@ -79,7 +79,7 @@ class BertConfig(object):
                 layer in the Transformer encoder.
             hidden_act: The non-linear activation function (function or string) in the
                 encoder and pooler.
-            hidden_dropout_prob: The dropout probabilitiy for all fully connected
+            hidden_dropout_prob: The dropout probability for all fully connected
                 layers in the embeddings, encoder, and pooler.
             attention_probs_dropout_prob: The dropout ratio for the attention
                 probabilities.

modelscope/models/multi_modal/prost/models/module_cross.py

@@ -51,7 +51,7 @@ class CrossConfig(PreCrossConfig):
                 layer in the Transformer encoder.
             hidden_act: The non-linear activation function (function or string) in the
                 encoder and pooler. If string, "gelu", "relu" and "swish" are supported.
-            hidden_dropout_prob: The dropout probabilitiy for all fully connected
+            hidden_dropout_prob: The dropout probability for all fully connected
                 layers in the embeddings, encoder, and pooler.
             attention_probs_dropout_prob: The dropout ratio for the attention
                 probabilities.

modelscope/models/nlp/mglm/model/modeling_bert.py

@@ -203,7 +203,7 @@ class BertConfig(object):
                 layer in the Transformer encoder.
             hidden_act: The non-linear activation function (function or string) in the
                 encoder and pooler. If string, "gelu", "relu" and "swish" are supported.
-            hidden_dropout_prob: The dropout probabilitiy for all fully connected
+            hidden_dropout_prob: The dropout probability for all fully connected
                 layers in the embeddings, encoder, and pooler.
             attention_probs_dropout_prob: The dropout ratio for the attention
                 probabilities.
@@ -743,7 +743,7 @@ class BertPreTrainingHeads(nn.Module):
 
 class PreTrainedBertModel(nn.Module):
     """ An abstract class to handle weights initialization and
-        a simple interface for dowloading and loading pretrained models.
+        a simple interface for downloading and loading pretrained models.
     """
 
     def __init__(self, config, *inputs, **kwargs):
@@ -799,7 +799,7 @@ class PreTrainedBertModel(nn.Module):
                     . `bert_config.json` a configuration file for the model
                     . `pytorch_model.bin` a PyTorch dump of a BertForPreTraining instance
             cache_dir: an optional path to a folder in which the pre-trained models will be cached.
-            state_dict: an optional state dictionnary (collections.OrderedDict object) to use instead of Google pre-trained models
+            state_dict: an optional state dictionary (collections.OrderedDict object) to use instead of Google pre-trained models
             *inputs, **kwargs: additional input for the specific Bert class
                 (ex: num_labels for BertForSequenceClassification)
         """ # noqa

modelscope/models/nlp/mglm/model/transformer.py

@@ -155,7 +155,7 @@ class ParallelSelfAttention(torch.nn.Module):
     """Parallel self-attention layer for GPT2.
 
     Self-attention layer takes input with size [b, s, h] where b is
-    the batch size, s is the sequence lenght, and h is the hidden size
+    the batch size, s is the sequence length, and h is the hidden size
     and creates output of the same size.
     Arguments:
         hidden_size: total hidden size of the layer (h).

modelscope/models/nlp/space_T_cn/backbone.py

@@ -656,7 +656,7 @@ class PreTrainedBertModel(nn.Module):
                     . `bert_config.json` a configuration file for the model
                     . `pytorch_model.bin` a PyTorch dump of a BertForPreTraining instance
             cache_dir: an optional path to a folder in which the pre-trained models will be cached.
-            state_dict: an optional state dictionnary (collections.OrderedDict object)
+            state_dict: an optional state dictionary (collections.OrderedDict object)
                 to use instead of Google pre-trained models
             *inputs, **kwargs: additional input for the specific Bert class
                 (ex: num_labels for BertForSequenceClassification)

modelscope/models/nlp/space_T_cn/configuration.py

@@ -52,7 +52,7 @@ class SpaceTCnConfig(object):
                 layer in the Transformer encoder.
             hidden_act: The non-linear activation function (function or string) in the
                 encoder and pooler. If string, "gelu", "relu" and "swish" are supported.
-            hidden_dropout_prob: The dropout probabilitiy for all fully connected
+            hidden_dropout_prob: The dropout probability for all fully connected
                 layers in the embeddings, encoder, and pooler.
             attention_probs_dropout_prob: The dropout ratio for the attention
                 probabilities.