add model

preprocessor_config.json

@@ -0,0 +1,13 @@
+{
+  "auto_map": {
+    "AutoProcessor": "processor_wav2vec2_new.Wav2Vec2ProcessorNew"
+  },
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "Wav2Vec2ProcessorNew",
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}

processor_wav2vec2_new.py

@@ -0,0 +1,106 @@
+# coding=utf-8
+# Copyright 2021 The HuggingFace Inc. team.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+"""
+Speech processor class for Wav2Vec2
+"""
+import warnings
+from contextlib import contextmanager
+
+from transformers import ProcessorMixin
+from transformers import Wav2Vec2FeatureExtractor
+from transformers import Wav2Vec2CTCTokenizer
+
+
+class Wav2Vec2ProcessorNew(ProcessorMixin):
+    r"""
+    Constructs a Wav2Vec2 processor which wraps a Wav2Vec2 feature extractor and a Wav2Vec2 CTC tokenizer into a single
+    processor.
+
+    [`Wav2Vec2Processor`] offers all the functionalities of [`Wav2Vec2FeatureExtractor`] and [`PreTrainedTokenizer`].
+    See the docstring of [`~Wav2Vec2Processor.__call__`] and [`~Wav2Vec2Processor.decode`] for more information.
+
+    Args:
+        feature_extractor (`Wav2Vec2FeatureExtractor`):
+            An instance of [`Wav2Vec2FeatureExtractor`]. The feature extractor is a required input.
+        tokenizer ([`PreTrainedTokenizer`]):
+            An instance of [`PreTrainedTokenizer`]. The tokenizer is a required input.
+    """
+    feature_extractor_class = "Wav2Vec2FeatureExtractor"
+    tokenizer_class = "AutoTokenizer"
+
+    def __init__(self, feature_extractor, tokenizer):
+        super().__init__(feature_extractor, tokenizer)
+        self.current_processor = self.feature_extractor
+
+    @classmethod
+    def from_pretrained(cls, pretrained_model_name_or_path, **kwargs):
+        try:
+            return super().from_pretrained(pretrained_model_name_or_path, **kwargs)
+        except OSError:
+            warnings.warn(
+                f"Loading a tokenizer inside {cls.__name__} from a config that does not"
+                " include a `tokenizer_class` attribute is deprecated and will be "
+                "removed in v5. Please add `'tokenizer_class': 'Wav2Vec2CTCTokenizer'`"
+                " attribute to either your `config.json` or `tokenizer_config.json` "
+                "file to suppress this warning: ",
+                FutureWarning,
+            )
+
+            feature_extractor = Wav2Vec2FeatureExtractor.from_pretrained(pretrained_model_name_or_path, **kwargs)
+            tokenizer = Wav2Vec2CTCTokenizer.from_pretrained(pretrained_model_name_or_path, **kwargs)
+
+            return cls(feature_extractor=feature_extractor, tokenizer=tokenizer)
+
+    def __call__(self, *args, **kwargs):
+        """
+        When used in normal mode, this method forwards all its arguments to Wav2Vec2FeatureExtractor's
+        [`~Wav2Vec2FeatureExtractor.__call__`] and returns its output. If used in the context
+        [`~Wav2Vec2Processor.as_target_processor`] this method forwards all its arguments to PreTrainedTokenizer's
+        [`~PreTrainedTokenizer.__call__`]. Please refer to the docstring of the above two methods for more information.
+        """
+        return self.current_processor(*args, **kwargs)
+
+    def pad(self, *args, **kwargs):
+        """
+        When used in normal mode, this method forwards all its arguments to Wav2Vec2FeatureExtractor's
+        [`~Wav2Vec2FeatureExtractor.pad`] and returns its output. If used in the context
+        [`~Wav2Vec2Processor.as_target_processor`] this method forwards all its arguments to PreTrainedTokenizer's
+        [`~PreTrainedTokenizer.pad`]. Please refer to the docstring of the above two methods for more information.
+        """
+        return self.current_processor.pad(*args, **kwargs)
+
+    def batch_decode(self, *args, **kwargs):
+        """
+        This method forwards all its arguments to PreTrainedTokenizer's [`~PreTrainedTokenizer.batch_decode`]. Please
+        refer to the docstring of this method for more information.
+        """
+        return self.tokenizer.batch_decode(*args, **kwargs)
+
+    def decode(self, *args, **kwargs):
+        """
+        This method forwards all its arguments to PreTrainedTokenizer's [`~PreTrainedTokenizer.decode`]. Please refer
+        to the docstring of this method for more information.
+        """
+        return self.tokenizer.decode(*args, **kwargs)
+
+    @contextmanager
+    def as_target_processor(self):
+        """
+        Temporarily sets the tokenizer for processing the input. Useful for encoding the labels when fine-tuning
+        Wav2Vec2.
+        """
+        self.current_processor = self.tokenizer
+        yield
+        self.current_processor = self.feature_extractor

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "<pad>", "do_lower_case": false, "word_delimiter_token": "|", "special_tokens_map_file": null, "name_or_path": "hf-internal-testing/processor_with_lm", "auto_map": {"AutoProcessor": "processor_wav2vec2_new.Wav2Vec2ProcessorNew"}, "tokenizer_class": "Wav2Vec2CTCTokenizer", "processor_class": "Wav2Vec2ProcessorNew"}

vocab.json

@@ -0,0 +1 @@
+{"|": 0, "<pad>": 1, "<unk>": 2, "<s>": 3, "</s>": 4, "a": 5, "b": 6, "c": 7, "d": 8, "e": 9, "f": 10, "g": 11, "h": 12, "i": 13, "j": 14, "k": 15}