Update README.md

README.md

@@ -0,0 +1,19 @@
+---
+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

@@ -1,9 +1,8 @@
 {
   "architectures": [
-    "AudioSpectrogramTransformerForSequenceClassification"
+    "ASTForAudioClassification"
   ],
   "attention_probs_dropout_prob": 0.0,
-  "frequency_dimension": 128,
   "frequency_stride": 10,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.0,
@@ -1069,12 +1068,13 @@
     "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

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