README.md

@@ -1,19 +0,0 @@
----
-license: bsd-3-clause
-tags:
-- audio-classification
----
-
-# Audio Spectrogram Transformer (fine-tuned on AudioSet) 
-
-Audio Spectrogram Transformer (AST) model fine-tuned on AudioSet. It was introduced in the paper [AST: Audio Spectrogram Transformer](https://arxiv.org/abs/2104.01778) by Gong et al. and first released in [this repository](https://github.com/YuanGongND/ast). 
-
-Disclaimer: The team releasing Audio Spectrogram Transformer did not write a model card for this model so this model card has been written by the Hugging Face team.
-
-## Model description
-
-The Audio Spectrogram Transformer is equivalent to [ViT](https://huggingface.co/docs/transformers/model_doc/vit), but applied on audio. Audio is first turned into an image (as a spectrogram), after which a Vision Transformer is applied. The model gets state-of-the-art results on several audio classification benchmarks.
-
-## Usage
-
-You can use the raw model for classifying audio into one of the AudioSet classes. See the [documentation](https://huggingface.co/docs/transformers/main/en/model_doc/audio-spectrogram-transformer#transformers.ASTForAudioClassification.forward.example) for more info.

config.json

@@ -1,8 +1,9 @@
 {
   "architectures": [
-    "ASTForAudioClassification"
+    "AudioSpectrogramTransformerForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.0,
+  "frequency_dimension": 128,
   "frequency_stride": 10,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.0,
@@ -1068,13 +1069,12 @@
     "Zither": 150
   },
   "layer_norm_eps": 1e-12,
-  "max_length": 1024,
   "model_type": "audio-spectrogram-transformer",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
-  "num_mel_bins": 128,
   "patch_size": 16,
   "qkv_bias": true,
+  "time_dimension": 1024,
   "time_stride": 10,
   "torch_dtype": "float32",
   "transformers_version": "4.25.0.dev0"

preprocessor_config.json

@@ -1,8 +1,7 @@
 {
   "do_normalize": true,
-  "feature_extractor_type": "ASTFeatureExtractor",
+  "feature_extractor_type": "AudioSpectrogramTransformerFeatureExtractor",
   "feature_size": 1,
-  "max_length": 1024,
   "mean": -4.2677393,
   "num_mel_bins": 128,
   "padding_side": "right",