first

README.md

@@ -0,0 +1,87 @@
+---
+license: apache-2.0
+base_model: facebook/wav2vec2-base
+tags:
+- generated_from_trainer
+datasets:
+- audiofolder
+metrics:
+- accuracy
+model-index:
+- name: my_awesome_mind_model
+  results:
+  - task:
+      name: Audio Classification
+      type: audio-classification
+    dataset:
+      name: audiofolder
+      type: audiofolder
+      config: default
+      split: train
+      args: default
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.9805375347544022
+---
+
+<!-- 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. -->
+
+# my_awesome_mind_model
+
+This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the audiofolder dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1816
+- Accuracy: 0.9805
+
+## 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: 128
+- eval_batch_size: 128
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 512
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 2.267         | 1.0   | 120  | 2.0147          | 0.9626   |
+| 1.309         | 2.0   | 240  | 1.0828          | 0.9731   |
+| 0.8739        | 2.99  | 360  | 0.6753          | 0.9759   |
+| 0.6183        | 4.0   | 481  | 0.4492          | 0.9781   |
+| 0.4868        | 5.0   | 601  | 0.3346          | 0.9771   |
+| 0.4124        | 6.0   | 721  | 0.2606          | 0.9787   |
+| 0.3495        | 6.99  | 841  | 0.2214          | 0.9808   |
+| 0.3073        | 8.0   | 962  | 0.2032          | 0.9790   |
+| 0.3264        | 9.0   | 1082 | 0.1862          | 0.9812   |
+| 0.3035        | 9.98  | 1200 | 0.1816          | 0.9805   |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.0.0
+- Datasets 2.15.0
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,186 @@
+{
+  "_name_or_path": "facebook/wav2vec2-base",
+  "activation_dropout": 0.0,
+  "adapter_attn_dim": null,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 256,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": false,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "sum",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": false,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.1,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "freeze_feat_extract_train": true,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "_background_noise_",
+    "1": "audio",
+    "10": "go",
+    "11": "happy",
+    "12": "house",
+    "13": "left",
+    "14": "marvin",
+    "15": "nine",
+    "16": "no",
+    "17": "off",
+    "18": "on",
+    "19": "one",
+    "2": "bed",
+    "20": "right",
+    "21": "seven",
+    "22": "sheila",
+    "23": "six",
+    "24": "stop",
+    "25": "three",
+    "26": "tree",
+    "27": "two",
+    "28": "up",
+    "29": "wow",
+    "3": "bird",
+    "30": "yes",
+    "31": "zero",
+    "4": "cat",
+    "5": "dog",
+    "6": "down",
+    "7": "eight",
+    "8": "five",
+    "9": "four"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "_background_noise_": "0",
+    "audio": "1",
+    "bed": "2",
+    "bird": "3",
+    "cat": "4",
+    "dog": "5",
+    "down": "6",
+    "eight": "7",
+    "five": "8",
+    "four": "9",
+    "go": "10",
+    "happy": "11",
+    "house": "12",
+    "left": "13",
+    "marvin": "14",
+    "nine": "15",
+    "no": "16",
+    "off": "17",
+    "on": "18",
+    "one": "19",
+    "right": "20",
+    "seven": "21",
+    "sheila": "22",
+    "six": "23",
+    "stop": "24",
+    "three": "25",
+    "tree": "26",
+    "two": "27",
+    "up": "28",
+    "wow": "29",
+    "yes": "30",
+    "zero": "31"
+  },
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0,
+  "mask_channel_length": 10,
+  "mask_channel_min_space": 1,
+  "mask_channel_other": 0.0,
+  "mask_channel_prob": 0.0,
+  "mask_channel_selection": "static",
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_min_space": 1,
+  "mask_time_other": 0.0,
+  "mask_time_prob": 0.05,
+  "mask_time_selection": "static",
+  "model_type": "wav2vec2",
+  "no_mask_channel_overlap": false,
+  "no_mask_time_overlap": false,
+  "num_adapter_layers": 3,
+  "num_attention_heads": 12,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 12,
+  "num_negatives": 100,
+  "output_hidden_size": 768,
+  "pad_token_id": 0,
+  "proj_codevector_dim": 256,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32,
+  "xvector_output_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:373af34163799ac9cf8cbfc0af69b298dc291e604aee8cafdad7aacd349cfe43
+size 378333160

preprocessor_config.json

@@ -0,0 +1,9 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}

runs/Nov27_09-41-10_34627fe27eea/events.out.tfevents.1701078076.34627fe27eea.47.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d413a9d67493d97d2c90d72e62e1a1969487ea186c9479e78b038c3736b6d4a
+size 7133

runs/Nov27_09-51-53_34627fe27eea/events.out.tfevents.1701078716.34627fe27eea.47.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf3bd9e881f2a23e0c1be3c97a0429bb00a1977f87b905ea5cc09654f1fc3ffb
+size 7133

runs/Nov27_09-57-50_34627fe27eea/events.out.tfevents.1701079071.34627fe27eea.47.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9eb63a3a3bfed7b3a96ec04c367c183cc45672862a1a5063f8738bd608d97f84
+size 7133

runs/Nov27_09-59-31_34627fe27eea/events.out.tfevents.1701079172.34627fe27eea.47.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf73179fd80a5fafa3731d629b38f4788fa45c781421ff427cdf56f9da52e960
+size 7133

runs/Nov27_10-01-39_34627fe27eea/events.out.tfevents.1701079300.34627fe27eea.47.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc05ede20c35a99cd1b2c8a548cf7fc8127bf2ab8481d2a5d060277278b8a195
+size 7450

runs/Nov27_10-02-55_34627fe27eea/events.out.tfevents.1701079377.34627fe27eea.47.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70388112a08f4687bd1b70aa3a6a59722b2383536e4d385ba7ab869499a8fa93
+size 7133

runs/Nov27_10-03-21_34627fe27eea/events.out.tfevents.1701079406.34627fe27eea.47.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2312dfb87ddaedfbbc5bb6c8a78b7294c22331a75c0bedb29a92bdbc1d3c70b6
+size 29518

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54c50b06da89a4db2ba6e3554e1b16d847ff7b6f7f1144f316e04be878cb1820
+size 4155