model addition (imports etc)

docs/source/en/_toctree.yml

@@ -490,6 +490,8 @@
         title: mLUKE
       - local: model_doc/mobilebert
         title: MobileBERT
+      - local: model_doc/moonshine
+        title: moonshine
       - local: model_doc/mpnet
         title: MPNet
       - local: model_doc/mpt

docs/source/en/model_doc/moonshine.md

@@ -0,0 +1,108 @@
+<!--Copyright 2024 The HuggingFace Team. All rights reserved.
+
+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.
+
+⚠️ Note that this file is in Markdown but contain specific syntax for our doc-builder (similar to MDX) that may not be
+rendered properly in your Markdown viewer.
+
+-->
+
+# moonshine
+
+# moonshine
+
+## Overview
+
+The moonshine model was proposed in [<INSERT PAPER NAME HERE>](<INSERT PAPER LINK HERE>) by <INSERT AUTHORS HERE>.
+<INSERT SHORT SUMMARY HERE>
+
+The abstract from the paper is the following:
+
+*<INSERT PAPER ABSTRACT HERE>*
+
+Tips:
+
+<INSERT TIPS ABOUT MODEL HERE>
+
+This model was contributed by [INSERT YOUR HF USERNAME HERE](https://huggingface.co/<INSERT YOUR HF USERNAME HERE>).
+The original code can be found [here](<INSERT LINK TO GITHUB REPO HERE>).
+
+
+## MoonshineConfig
+
+[[autodoc]] MoonshineConfig
+
+## MoonshineTokenizer
+
+[[autodoc]] MoonshineTokenizer
+    - set_prefix_tokens
+    - build_inputs_with_special_tokens
+    - get_special_tokens_mask
+    - create_token_type_ids_from_sequences
+    - save_vocabulary
+    - batch_decode
+    - decode
+    - basic_normalize
+    - normalize
+
+## MoonshineTokenizerFast
+
+[[autodoc]] MoonshineTokenizerFast
+    - set_prefix_tokens
+    - build_inputs_with_special_tokens
+    - get_special_tokens_mask
+    - create_token_type_ids_from_sequences
+    - save_vocabulary
+    - batch_decode
+    - decode
+    - basic_normalize
+    - normalize
+
+## MoonshineFeatureExtractor
+
+[[autodoc]] MoonshineFeatureExtractor
+    - __call__
+
+## MoonshineProcessor
+
+[[autodoc]] MoonshineProcessor
+    - __call__
+    - from_pretrained
+    - save_pretrained
+    - batch_decode
+    - decode
+
+<frameworkcontent>
+<pt>
+
+## MoonshineModel
+
+[[autodoc]] MoonshineModel
+    - forward
+    - _mask_input_features
+
+## MoonshineForConditionalGeneration
+
+[[autodoc]] MoonshineForConditionalGeneration
+    - forward
+    - generate
+
+## MoonshineForCausalLM
+
+[[autodoc]] MoonshineForCausalLM
+    - forward
+
+## MoonshineForAudioClassification
+
+[[autodoc]] MoonshineForAudioClassification
+    - forward
+
+</pt>
+<tf>

src/transformers/__init__.py

@@ -463,6 +463,7 @@
     "models.gpt_bigcode": ["GPTBigCodeConfig"],
     "models.gpt_neo": ["GPTNeoConfig"],
     "models.gpt_neox": ["GPTNeoXConfig"],
+    "models.moonshine": ["MoonshineConfig"],
     "models.gpt_neox_japanese": ["GPTNeoXJapaneseConfig"],
     "models.gpt_sw3": [],
     "models.gptj": ["GPTJConfig"],
@@ -1081,6 +1082,7 @@
     _import_structure["models.gemma"].append("GemmaTokenizerFast")
     _import_structure["models.gpt2"].append("GPT2TokenizerFast")
     _import_structure["models.gpt_neox"].append("GPTNeoXTokenizerFast")
+    _import_structure["models.moonshine"].append("MoonshineTokenizer")
     _import_structure["models.gpt_neox_japanese"].append("GPTNeoXJapaneseTokenizer")
     _import_structure["models.herbert"].append("HerbertTokenizerFast")
     _import_structure["models.layoutlm"].append("LayoutLMTokenizerFast")
@@ -2360,6 +2362,16 @@
             "GPTNeoXPreTrainedModel",
         ]
     )
+    _import_structure["models.moonshine"].extend(
+        [
+            "MoonshineForCausalLM",
+            "MoonshineForQuestionAnswering",
+            "MoonshineForSequenceClassification",
+            "MoonshineForTokenClassification",
+            "MoonshineModel",
+            "MoonshinePreTrainedModel",
+        ]
+    )
     _import_structure["models.gpt_neox_japanese"].extend(
         [
             "GPTNeoXJapaneseForCausalLM",
@@ -5339,6 +5351,7 @@
     )
     from .models.gpt_neo import GPTNeoConfig
     from .models.gpt_neox import GPTNeoXConfig
+    from .models.moonshine import MoonshineConfig
     from .models.gpt_neox_japanese import (
         GPTNeoXJapaneseConfig,
     )
@@ -6009,6 +6022,7 @@
         from .models.gemma import GemmaTokenizerFast
         from .models.gpt2 import GPT2TokenizerFast
         from .models.gpt_neox import GPTNeoXTokenizerFast
+        from .models.moonshine import MoonshineTokenizer
         from .models.gpt_neox_japanese import GPTNeoXJapaneseTokenizer
         from .models.herbert import HerbertTokenizerFast
         from .models.layoutlm import LayoutLMTokenizerFast
@@ -7102,6 +7116,14 @@
             GPTNeoXModel,
             GPTNeoXPreTrainedModel,
         )
+        from .models.moonshine import (
+            MoonshineForCausalLM,
+            MoonshineForQuestionAnswering,
+            MoonshineForSequenceClassification,
+            MoonshineForTokenClassification,
+            MoonshineModel,
+            MoonshinePreTrainedModel,
+        )
         from .models.gpt_neox_japanese import (
             GPTNeoXJapaneseForCausalLM,
             GPTNeoXJapaneseModel,

src/transformers/models/__init__.py

@@ -103,6 +103,7 @@
     gpt_bigcode,
     gpt_neo,
     gpt_neox,
+    moonshine,
     gpt_neox_japanese,
     gpt_sw3,
     gptj,

src/transformers/models/auto/configuration_auto.py

@@ -121,6 +121,7 @@
         ("gpt_bigcode", "GPTBigCodeConfig"),
         ("gpt_neo", "GPTNeoConfig"),
         ("gpt_neox", "GPTNeoXConfig"),
+        ("moonshine", "MoonshineConfig"),
         ("gpt_neox_japanese", "GPTNeoXJapaneseConfig"),
         ("gptj", "GPTJConfig"),
         ("gptsan-japanese", "GPTSanJapaneseConfig"),
@@ -425,6 +426,7 @@
         ("gpt_bigcode", "GPTBigCode"),
         ("gpt_neo", "GPT Neo"),
         ("gpt_neox", "GPT NeoX"),
+        ("moonshine", "moonshine"),
         ("gpt_neox_japanese", "GPT NeoX Japanese"),
         ("gptj", "GPT-J"),
         ("gptsan-japanese", "GPTSAN-japanese"),

src/transformers/models/auto/modeling_auto.py

@@ -118,6 +118,7 @@
         ("gpt_bigcode", "GPTBigCodeModel"),
         ("gpt_neo", "GPTNeoModel"),
         ("gpt_neox", "GPTNeoXModel"),
+        ("moonshine", "MoonshineModel"),
         ("gpt_neox_japanese", "GPTNeoXJapaneseModel"),
         ("gptj", "GPTJModel"),
         ("gptsan-japanese", "GPTSanJapaneseForConditionalGeneration"),
@@ -408,6 +409,7 @@
         ("gpt_bigcode", "GPTBigCodeForCausalLM"),
         ("gpt_neo", "GPTNeoForCausalLM"),
         ("gpt_neox", "GPTNeoXForCausalLM"),
+        ("moonshine", "MoonshineForCausalLM"),
         ("gpt_neox_japanese", "GPTNeoXJapaneseForCausalLM"),
         ("gptj", "GPTJForCausalLM"),
         ("gptsan-japanese", "GPTSanJapaneseForConditionalGeneration"),
@@ -494,6 +496,7 @@
         ("gpt_bigcode", "GPTBigCodeForCausalLM"),
         ("gpt_neo", "GPTNeoForCausalLM"),
         ("gpt_neox", "GPTNeoXForCausalLM"),
+        ("moonshine", "MoonshineForCausalLM"),
         ("gpt_neox_japanese", "GPTNeoXJapaneseForCausalLM"),
         ("gptj", "GPTJForCausalLM"),
         ("granite", "GraniteForCausalLM"),
@@ -951,6 +954,7 @@
         ("gpt_bigcode", "GPTBigCodeForSequenceClassification"),
         ("gpt_neo", "GPTNeoForSequenceClassification"),
         ("gpt_neox", "GPTNeoXForSequenceClassification"),
+        ("moonshine", "MoonshineForSequenceClassification"),
         ("gptj", "GPTJForSequenceClassification"),
         ("ibert", "IBertForSequenceClassification"),
         ("jamba", "JambaForSequenceClassification"),
@@ -1039,6 +1043,7 @@
         ("gpt2", "GPT2ForQuestionAnswering"),
         ("gpt_neo", "GPTNeoForQuestionAnswering"),
         ("gpt_neox", "GPTNeoXForQuestionAnswering"),
+        ("moonshine", "MoonshineForQuestionAnswering"),
         ("gptj", "GPTJForQuestionAnswering"),
         ("ibert", "IBertForQuestionAnswering"),
         ("layoutlmv2", "LayoutLMv2ForQuestionAnswering"),
@@ -1142,6 +1147,7 @@
         ("gpt_bigcode", "GPTBigCodeForTokenClassification"),
         ("gpt_neo", "GPTNeoForTokenClassification"),
         ("gpt_neox", "GPTNeoXForTokenClassification"),
+        ("moonshine", "MoonshineForTokenClassification"),
         ("ibert", "IBertForTokenClassification"),
         ("layoutlm", "LayoutLMForTokenClassification"),
         ("layoutlmv2", "LayoutLMv2ForTokenClassification"),

src/transformers/models/auto/tokenization_auto.py

@@ -311,6 +311,7 @@
             ("mluke", ("MLukeTokenizer" if is_sentencepiece_available() else None, None)),
             ("mobilebert", ("MobileBertTokenizer", "MobileBertTokenizerFast" if is_tokenizers_available() else None)),
             ("moshi", (None, "PreTrainedTokenizerFast" if is_tokenizers_available() else None)),
+            ("moonshine", (None, "PreTrainedTokenizerFast" if is_tokenizers_available() else None)),
             ("mpnet", ("MPNetTokenizer", "MPNetTokenizerFast" if is_tokenizers_available() else None)),
             ("mpt", (None, "GPTNeoXTokenizerFast" if is_tokenizers_available() else None)),
             ("mra", ("RobertaTokenizer", "RobertaTokenizerFast" if is_tokenizers_available() else None)),

src/transformers/models/moonshine/__init__.py

@@ -30,9 +30,13 @@
 except OptionalDependencyNotAvailable:
     pass
 else:
-    _import_structure["modeling_gemma2"] = [
+    _import_structure["modeling_moonshine"] = [
+        "MoonshineForConditionalGeneration",
+        "MoonshineModel",
+        "MoonshinePreTrainedModel",
     ]
 
+
 if TYPE_CHECKING:
     from .configuration_moonshine import MoonshineConfig
 
@@ -42,7 +46,12 @@
     except OptionalDependencyNotAvailable:
         pass
     else:
-        pass
+        from .modeling_moonshine import (
+            MoonshineForConditionalGeneration,
+            MoonshineModel,
+            MoonshinePreTrainedModel,
+        )
+
 
 else:
     import sys