bit3ca/ast-finetuned-speech-commands-bit3

README.md

@@ -0,0 +1,67 @@
+---
+license: bsd-3-clause
+base_model: MIT/ast-finetuned-speech-commands-v2
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: ast-finetuned-speech-commands-bit3
+  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-bit3
+
+This model is a fine-tuned version of [MIT/ast-finetuned-speech-commands-v2](https://huggingface.co/MIT/ast-finetuned-speech-commands-v2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4409
+- Accuracy: 0.9031
+
+## 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: 3e-05
+- train_batch_size: 36
+- eval_batch_size: 36
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 144
+- 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 |
+|:-------------:|:-----:|:----:|:--------:|:---------------:|
+| 0.0583        | 1.0   | 589  | 0.8992   | 0.4810          |
+| 0.0628        | 2.0   | 1178 | 0.9031   | 0.4409          |
+| 0.0218        | 3.0   | 1767 | 0.9010   | 0.4444          |
+| 0.0092        | 4.0   | 2356 | 0.9012   | 0.4322          |
+| 0.0148        | 5.0   | 2945 | 0.9031   | 0.3927          |
+
+
+### Framework versions
+
+- Transformers 4.37.1
+- Pytorch 2.1.0+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.1

config.json

@@ -0,0 +1,101 @@
+{
+  "_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": "yes",
+    "1": "no",
+    "10": "zero",
+    "11": "one",
+    "12": "two",
+    "13": "three",
+    "14": "four",
+    "15": "five",
+    "16": "six",
+    "17": "seven",
+    "18": "eight",
+    "19": "nine",
+    "2": "up",
+    "20": "bed",
+    "21": "bird",
+    "22": "cat",
+    "23": "dog",
+    "24": "happy",
+    "25": "house",
+    "26": "marvin",
+    "27": "sheila",
+    "28": "tree",
+    "29": "wow",
+    "3": "down",
+    "30": "backward",
+    "31": "forward",
+    "32": "follow",
+    "33": "learn",
+    "34": "visual",
+    "35": "_silence_",
+    "4": "left",
+    "5": "right",
+    "6": "on",
+    "7": "off",
+    "8": "stop",
+    "9": "go"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "_silence_": "35",
+    "backward": "30",
+    "bed": "20",
+    "bird": "21",
+    "cat": "22",
+    "dog": "23",
+    "down": "3",
+    "eight": "18",
+    "five": "15",
+    "follow": "32",
+    "forward": "31",
+    "four": "14",
+    "go": "9",
+    "happy": "24",
+    "house": "25",
+    "learn": "33",
+    "left": "4",
+    "marvin": "26",
+    "nine": "19",
+    "no": "1",
+    "off": "7",
+    "on": "6",
+    "one": "11",
+    "right": "5",
+    "seven": "17",
+    "sheila": "27",
+    "six": "16",
+    "stop": "8",
+    "three": "13",
+    "tree": "28",
+    "two": "12",
+    "up": "2",
+    "visual": "34",
+    "wow": "29",
+    "yes": "0",
+    "zero": "10"
+  },
+  "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": "4.37.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9801a531c193137cd051f10072d3fab0cf5aabf11728df5381372654ac8f5d30
+size 341613728

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
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84c8df1001bc19ae470ecc1772bbc9f59d18c8fb981352ad63604eff11a41eb1
+size 4728