End of training

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

README.md

@@ -0,0 +1,66 @@
+---
+license: bsd-3-clause
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: ast-finetuned-speech-commands-v2-finetuned
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# ast-finetuned-speech-commands-v2-finetuned
+
+This model is a fine-tuned version of [MIT/ast-finetuned-speech-commands-v2](https://huggingface.co/MIT/ast-finetuned-speech-commands-v2) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0268
+- Accuracy: 0.9958
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-07
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 128
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 5
+
+### Training results
+
+| Training Loss | Epoch | Step  | Accuracy | Validation Loss |
+|:-------------:|:-----:|:-----:|:--------:|:---------------:|
+| 0.1781        | 1.0   | 8558  | 0.9970   | 0.1609          |
+| 0.0217        | 2.0   | 17116 | 0.9979   | 0.0210          |
+| 0.018         | 3.0   | 25674 | 0.9979   | 0.0144          |
+| 0.0215        | 4.0   | 34232 | 0.9976   | 0.0129          |
+| 0.0407        | 5.0   | 42790 | 0.0126   | 0.9976          |
+
+
+### Framework versions
+
+- Transformers 4.26.1
+- Pytorch 1.11.0
+- Datasets 2.10.0
+- Tokenizers 0.12.1

config.json

@@ -0,0 +1,53 @@
+{
+  "_name_or_path": "MIT/ast-finetuned-speech-commands-v2",
+  "architectures": [
+    "ASTForAudioClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "frequency_stride": 10,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "zero",
+    "1": "one",
+    "10": "#unk#",
+    "11": "#pub#",
+    "2": "two",
+    "3": "three",
+    "4": "four",
+    "5": "five",
+    "6": "six",
+    "7": "seven",
+    "8": "eight",
+    "9": "nine"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "#pub#": 11,
+    "#unk#": 10,
+    "eight": 8,
+    "five": 5,
+    "four": 4,
+    "nine": 9,
+    "one": 1,
+    "seven": 7,
+    "six": 6,
+    "three": 3,
+    "two": 2,
+    "zero": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_length": 128,
+  "model_type": "audio-spectrogram-transformer",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "num_mel_bins": 128,
+  "patch_size": 16,
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "time_stride": 10,
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.1"
+}

preprocessor_config.json

@@ -0,0 +1,13 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "ASTFeatureExtractor",
+  "feature_size": 1,
+  "max_length": 128,
+  "mean": -6.845978,
+  "num_mel_bins": 128,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": false,
+  "sampling_rate": 16000,
+  "std": 5.5654526
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efb4441fc565f55eb07b3c7fecdedaa64df653022be67ffd6992164aea4b7d0c
+size 341580651

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:561a447d1c0db0b09a1668937e61d632c410ca94ecfde07d23df0e89b39a61d0
+size 3503