End of training

README.md

@@ -0,0 +1,91 @@
+---
+license: apache-2.0
+base_model: facebook/wav2vec2-base-960h
+tags:
+- generated_from_trainer
+datasets:
+- speech_commands
+metrics:
+- accuracy
+model-index:
+- name: wav2vec2-base-960h-speech-commands
+  results:
+  - task:
+      name: Audio Classification
+      type: audio-classification
+    dataset:
+      name: speech_commands
+      type: speech_commands
+      config: v0.02
+      split: None
+      args: v0.02
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.8066546762589928
+---
+
+<!-- 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. -->
+
+# wav2vec2-base-960h-speech-commands
+
+This model is a fine-tuned version of [facebook/wav2vec2-base-960h](https://huggingface.co/facebook/wav2vec2-base-960h) on the speech_commands dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.1612
+- Accuracy: 0.8067
+
+## 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: 5e-05
+- train_batch_size: 48
+- eval_batch_size: 48
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 20
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|
+| 1.745         | 1.0   | 824   | 1.9237          | 0.7648   |
+| 0.5664        | 2.0   | 1648  | 1.1424          | 0.7878   |
+| 0.4337        | 3.0   | 2472  | 1.1234          | 0.8013   |
+| 0.3346        | 4.0   | 3296  | 1.1040          | 0.8035   |
+| 0.2683        | 5.0   | 4120  | 1.3128          | 0.7905   |
+| 0.3498        | 6.0   | 4944  | 1.2172          | 0.7972   |
+| 0.2556        | 7.0   | 5768  | 1.1906          | 0.7986   |
+| 0.226         | 8.0   | 6592  | 1.1081          | 0.8044   |
+| 0.2317        | 9.0   | 7416  | 1.1068          | 0.8049   |
+| 0.1144        | 10.0  | 8240  | 1.1612          | 0.8067   |
+| 0.2143        | 11.0  | 9064  | 1.1577          | 0.8031   |
+| 0.1668        | 12.0  | 9888  | 1.1343          | 0.8058   |
+| 0.2504        | 13.0  | 10712 | 1.0583          | 0.8067   |
+| 0.218         | 14.0  | 11536 | 1.0677          | 0.8026   |
+| 0.1025        | 15.0  | 12360 | 1.0690          | 0.8053   |
+
+
+### Framework versions
+
+- Transformers 4.43.3
+- Pytorch 2.2.2+cu121
+- Datasets 2.18.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,186 @@
+{
+  "_name_or_path": "facebook/wav2vec2-base-960h",
+  "activation_dropout": 0.1,
+  "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_dropout": 0.0,
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.1,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.1,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_dropout_prob": 0.1,
+  "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-05,
+  "layerdrop": 0.1,
+  "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_prob": 0.05,
+  "model_type": "wav2vec2",
+  "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": "4.43.3",
+  "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:c4cb012de9cd287adbf3a6ee227e4f864892b9155f3d7d42341635798867fe23
+size 378337328

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/Oct01_09-41-03_ki-g0010/events.out.tfevents.1727775668.ki-g0010.1556905.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7d12623994a49ee3d266406eb288ad789db0648fe524c0a0db3bf3ec30f216c
+size 14436

runs/Oct01_09-42-21_ki-g0010/events.out.tfevents.1727775745.ki-g0010.1558728.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca2d23dec5109d95c761b89fbe97b4ac794b123d2190b81879fab52e39d234cf
+size 534475

runs/Oct01_09-42-21_ki-g0010/events.out.tfevents.1727776385.ki-g0010.1558728.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:183e2ae005fb6de96e55cdc43a7fb2310e00198a530fd0683d2feb1925cfc15d
+size 411

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92bd7d0e35cc2486fa36161532514b97569cc73d750fe9f5bb9c6beed575e714
+size 5240