Upload fine-tuned HUBERT vowel classifier

checkpoints/checkpoint-10916/config.json

@@ -0,0 +1,98 @@
+{
+  "activation_dropout": 0.1,
+  "apply_spec_augment": true,
+  "architectures": [
+    "HubertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "conv_bias": false,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_pos_batch_norm": false,
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "sum",
+  "ctc_zero_infinity": false,
+  "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_proj_layer_norm": true,
+  "final_dropout": 0.1,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8
+  },
+  "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": 0.0,
+  "model_type": "hubert",
+  "num_attention_heads": 12,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32
+}

checkpoints/checkpoint-10916/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a467102e2eca83185336bcd6488e3eee01fbba8c4a49e8074cfde44a0d53266d
+size 378309148

checkpoints/checkpoint-10916/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f192fc14c22f672367cb1dd14d62c7216e9dc8debf99e6cf19a762c37b3a631f
+size 756734475

checkpoints/checkpoint-10916/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6d08a5484f52cbb805c81b0a3ac668e47c0bb3f8fb5a45803e8cf1d5c9364a6
+size 14455

checkpoints/checkpoint-10916/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b6b3d374d162562d7181e35af847e336046d647cafbf1ee9adf8e902f093a19
+size 1465

checkpoints/checkpoint-10916/trainer_state.json

@@ -0,0 +1,98 @@
+{
+  "best_global_step": 10916,
+  "best_metric": 0.8916987355689939,
+  "best_model_checkpoint": "./fine_tuned_vowel_model_hubert/checkpoints/checkpoint-10916",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 10916,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.7431244850158691,
+      "learning_rate": 4.0003664345914255e-05,
+      "loss": 0.7026,
+      "step": 2729
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8449697636063771,
+      "eval_loss": 0.5954396724700928,
+      "eval_runtime": 13.4904,
+      "eval_samples_per_second": 404.511,
+      "eval_steps_per_second": 50.629,
+      "step": 2729
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.1394549012184143,
+      "learning_rate": 3.0003664345914256e-05,
+      "loss": 0.4608,
+      "step": 5458
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8792376763789628,
+      "eval_loss": 0.5260357856750488,
+      "eval_runtime": 12.9279,
+      "eval_samples_per_second": 422.112,
+      "eval_steps_per_second": 52.832,
+      "step": 5458
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 116.29024505615234,
+      "learning_rate": 2.0003664345914254e-05,
+      "loss": 0.371,
+      "step": 8187
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8887667216419278,
+      "eval_loss": 0.5250139236450195,
+      "eval_runtime": 12.4693,
+      "eval_samples_per_second": 437.635,
+      "eval_steps_per_second": 54.775,
+      "step": 8187
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 18.14418601989746,
+      "learning_rate": 1.0003664345914255e-05,
+      "loss": 0.2928,
+      "step": 10916
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8916987355689939,
+      "eval_loss": 0.57878178358078,
+      "eval_runtime": 12.1012,
+      "eval_samples_per_second": 450.946,
+      "eval_steps_per_second": 56.441,
+      "step": 10916
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 13645,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.803131179533748e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoints/checkpoint-10916/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3178195344f46f46b3031b675585d8c03b499e7d32bb87bf40496a15e9e1126
+size 5713

checkpoints/checkpoint-13645/config.json

@@ -0,0 +1,98 @@
+{
+  "activation_dropout": 0.1,
+  "apply_spec_augment": true,
+  "architectures": [
+    "HubertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "conv_bias": false,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_pos_batch_norm": false,
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "sum",
+  "ctc_zero_infinity": false,
+  "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_proj_layer_norm": true,
+  "final_dropout": 0.1,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8
+  },
+  "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": 0.0,
+  "model_type": "hubert",
+  "num_attention_heads": 12,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32
+}

checkpoints/checkpoint-13645/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e253002c57e573c2a7d2c6bb92948a0532b9471527eec6e154d4b71b819e6b7
+size 378309148

checkpoints/checkpoint-13645/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:173b8dc5d365bb15274565588dc12293988d45da5ab409bd7a207d74fde20c26
+size 756734475

checkpoints/checkpoint-13645/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea68a63b52eb6548d8b3f161d296b8f31e6c69810c9d3267393657d6694b91a0
+size 14455

checkpoints/checkpoint-13645/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b58bab2079a1e60f13455dd02b5b0d37795a4e3bd7bee0f5e83d482f80f5668
+size 1465

checkpoints/checkpoint-13645/trainer_state.json

@@ -0,0 +1,114 @@
+{
+  "best_global_step": 13645,
+  "best_metric": 0.8944474986256185,
+  "best_model_checkpoint": "./fine_tuned_vowel_model_hubert/checkpoints/checkpoint-13645",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 13645,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.7431244850158691,
+      "learning_rate": 4.0003664345914255e-05,
+      "loss": 0.7026,
+      "step": 2729
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8449697636063771,
+      "eval_loss": 0.5954396724700928,
+      "eval_runtime": 13.4904,
+      "eval_samples_per_second": 404.511,
+      "eval_steps_per_second": 50.629,
+      "step": 2729
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.1394549012184143,
+      "learning_rate": 3.0003664345914256e-05,
+      "loss": 0.4608,
+      "step": 5458
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8792376763789628,
+      "eval_loss": 0.5260357856750488,
+      "eval_runtime": 12.9279,
+      "eval_samples_per_second": 422.112,
+      "eval_steps_per_second": 52.832,
+      "step": 5458
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 116.29024505615234,
+      "learning_rate": 2.0003664345914254e-05,
+      "loss": 0.371,
+      "step": 8187
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8887667216419278,
+      "eval_loss": 0.5250139236450195,
+      "eval_runtime": 12.4693,
+      "eval_samples_per_second": 437.635,
+      "eval_steps_per_second": 54.775,
+      "step": 8187
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 18.14418601989746,
+      "learning_rate": 1.0003664345914255e-05,
+      "loss": 0.2928,
+      "step": 10916
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8916987355689939,
+      "eval_loss": 0.57878178358078,
+      "eval_runtime": 12.1012,
+      "eval_samples_per_second": 450.946,
+      "eval_steps_per_second": 56.441,
+      "step": 10916
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.16541193425655365,
+      "learning_rate": 3.664345914254306e-09,
+      "loss": 0.2333,
+      "step": 13645
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8944474986256185,
+      "eval_loss": 0.5925989747047424,
+      "eval_runtime": 12.2917,
+      "eval_samples_per_second": 443.957,
+      "eval_steps_per_second": 55.566,
+      "step": 13645
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 13645,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.2541662744176947e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoints/checkpoint-13645/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3178195344f46f46b3031b675585d8c03b499e7d32bb87bf40496a15e9e1126
+size 5713

checkpoints/checkpoint-2729/config.json

@@ -0,0 +1,98 @@
+{
+  "activation_dropout": 0.1,
+  "apply_spec_augment": true,
+  "architectures": [
+    "HubertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "conv_bias": false,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_pos_batch_norm": false,
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "sum",
+  "ctc_zero_infinity": false,
+  "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_proj_layer_norm": true,
+  "final_dropout": 0.1,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8
+  },
+  "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": 0.0,
+  "model_type": "hubert",
+  "num_attention_heads": 12,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32
+}

checkpoints/checkpoint-2729/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d6613875495014ea4d25c4f91f396ea1c979cf5c5f6dc1a06500f15fa8c1377
+size 378309148

checkpoints/checkpoint-2729/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b43504597ecfcb1b7e5956e4341b676c8e6198b6f1a79891b11742222b4e876
+size 756734475

checkpoints/checkpoint-2729/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea200907bf22a7285702a90c82fddb0bc9b345082a2ba718466e46ec3f624aaa
+size 14455

checkpoints/checkpoint-2729/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4170acc0e84df36b983756c50956178d160d8904ae138886c0fb61ec4c5ba556
+size 1465

checkpoints/checkpoint-2729/trainer_state.json

@@ -0,0 +1,50 @@
+{
+  "best_global_step": 2729,
+  "best_metric": 0.8449697636063771,
+  "best_model_checkpoint": "./fine_tuned_vowel_model_hubert/checkpoints/checkpoint-2729",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 2729,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.7431244850158691,
+      "learning_rate": 4.0003664345914255e-05,
+      "loss": 0.7026,
+      "step": 2729
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8449697636063771,
+      "eval_loss": 0.5954396724700928,
+      "eval_runtime": 13.4904,
+      "eval_samples_per_second": 404.511,
+      "eval_steps_per_second": 50.629,
+      "step": 2729
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 13645,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.505194187404075e+16,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoints/checkpoint-2729/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3178195344f46f46b3031b675585d8c03b499e7d32bb87bf40496a15e9e1126
+size 5713

checkpoints/checkpoint-5458/config.json

@@ -0,0 +1,98 @@
+{
+  "activation_dropout": 0.1,
+  "apply_spec_augment": true,
+  "architectures": [
+    "HubertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "conv_bias": false,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_pos_batch_norm": false,
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "sum",
+  "ctc_zero_infinity": false,
+  "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_proj_layer_norm": true,
+  "final_dropout": 0.1,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8
+  },
+  "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": 0.0,
+  "model_type": "hubert",
+  "num_attention_heads": 12,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32
+}

checkpoints/checkpoint-5458/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:027c836889b9c6dff7fcd845a987026d85f20a6de1a4acf5b7cab7f875d147c2
+size 378309148

checkpoints/checkpoint-5458/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a9ac2caf3feb93de932dc17c3dbada05d9bbdf09492f508999045ed85bc69c8
+size 756734475

checkpoints/checkpoint-5458/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e5067e2c971581835c48c8b92efce57577a076f65e6270573f525825609e404
+size 14455

checkpoints/checkpoint-5458/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99abf3f8d618bf535394d7da5d2a6f328625f877f33ac77786a006c0a8b59a30
+size 1465

checkpoints/checkpoint-5458/trainer_state.json

@@ -0,0 +1,66 @@
+{
+  "best_global_step": 5458,
+  "best_metric": 0.8792376763789628,
+  "best_model_checkpoint": "./fine_tuned_vowel_model_hubert/checkpoints/checkpoint-5458",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 5458,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.7431244850158691,
+      "learning_rate": 4.0003664345914255e-05,
+      "loss": 0.7026,
+      "step": 2729
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8449697636063771,
+      "eval_loss": 0.5954396724700928,
+      "eval_runtime": 13.4904,
+      "eval_samples_per_second": 404.511,
+      "eval_steps_per_second": 50.629,
+      "step": 2729
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.1394549012184143,
+      "learning_rate": 3.0003664345914256e-05,
+      "loss": 0.4608,
+      "step": 5458
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8792376763789628,
+      "eval_loss": 0.5260357856750488,
+      "eval_runtime": 12.9279,
+      "eval_samples_per_second": 422.112,
+      "eval_steps_per_second": 52.832,
+      "step": 5458
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 13645,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.019020502929226e+16,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoints/checkpoint-5458/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3178195344f46f46b3031b675585d8c03b499e7d32bb87bf40496a15e9e1126
+size 5713

checkpoints/checkpoint-8187/config.json

@@ -0,0 +1,98 @@
+{
+  "activation_dropout": 0.1,
+  "apply_spec_augment": true,
+  "architectures": [
+    "HubertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "conv_bias": false,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_pos_batch_norm": false,
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "sum",
+  "ctc_zero_infinity": false,
+  "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_proj_layer_norm": true,
+  "final_dropout": 0.1,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8
+  },
+  "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": 0.0,
+  "model_type": "hubert",
+  "num_attention_heads": 12,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32
+}

checkpoints/checkpoint-8187/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65c6145dc7273172cd887b4d26f71429024a6adf4e7a654073744dcfa4d53f42
+size 378309148

checkpoints/checkpoint-8187/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0dc441edf7cfcb4f8563751cf5f60d4f792c210c86bce9580403e60e86b54d91
+size 756734475

checkpoints/checkpoint-8187/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19a8e6f0588fe3d1f50ae60492a5ada2beb4972a53e6e5a6bd68c3c671f5091c
+size 14455

checkpoints/checkpoint-8187/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a223eaee1486f9a44419fc63bd3824ba990f5207fac40cf8a423f1da10ea85d
+size 1465

checkpoints/checkpoint-8187/trainer_state.json

@@ -0,0 +1,82 @@
+{
+  "best_global_step": 8187,
+  "best_metric": 0.8887667216419278,
+  "best_model_checkpoint": "./fine_tuned_vowel_model_hubert/checkpoints/checkpoint-8187",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 8187,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.7431244850158691,
+      "learning_rate": 4.0003664345914255e-05,
+      "loss": 0.7026,
+      "step": 2729
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8449697636063771,
+      "eval_loss": 0.5954396724700928,
+      "eval_runtime": 13.4904,
+      "eval_samples_per_second": 404.511,
+      "eval_steps_per_second": 50.629,
+      "step": 2729
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.1394549012184143,
+      "learning_rate": 3.0003664345914256e-05,
+      "loss": 0.4608,
+      "step": 5458
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8792376763789628,
+      "eval_loss": 0.5260357856750488,
+      "eval_runtime": 12.9279,
+      "eval_samples_per_second": 422.112,
+      "eval_steps_per_second": 52.832,
+      "step": 5458
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 116.29024505615234,
+      "learning_rate": 2.0003664345914254e-05,
+      "loss": 0.371,
+      "step": 8187
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8887667216419278,
+      "eval_loss": 0.5250139236450195,
+      "eval_runtime": 12.4693,
+      "eval_samples_per_second": 437.635,
+      "eval_steps_per_second": 54.775,
+      "step": 8187
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 13645,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.3531804571600885e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoints/checkpoint-8187/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3178195344f46f46b3031b675585d8c03b499e7d32bb87bf40496a15e9e1126
+size 5713

classification_report.csv

@@ -0,0 +1,13 @@
+,precision,recall,f1-score,support
+aː,0.9426791277258567,0.9322242760320394,0.9374225526641884,1623.0
+eː,0.9323308270676691,0.9127234490010515,0.922422954303932,951.0
+oː,0.9166666666666666,0.9166666666666666,0.9166666666666666,720.0
+æːɪ,0.8868421052631579,0.8753246753246753,0.8810457516339869,385.0
+æːʊ,0.6046511627906976,0.7602339181286549,0.6735751295336787,171.0
+ɑɪ,0.9067164179104478,0.9101123595505618,0.908411214953271,534.0
+ɑʊ,0.6820512820512821,0.6244131455399061,0.6519607843137255,213.0
+əʊ,0.8215962441314554,0.7990867579908676,0.8101851851851852,219.0
+ɜɪ,0.8746223564954683,0.9032761310452418,0.88871834228703,641.0
+accuracy,0.8944474986256185,0.8944474986256185,0.8944474986256185,0.8944474986256185
+macro avg,0.8409062433447446,0.8482290421421851,0.8433787312824071,5457.0
+weighted avg,0.8963662082505828,0.8944474986256185,0.8950161705793978,5457.0

config.json

@@ -56,7 +56,11 @@
     "1": "LABEL_1",
     "2": "LABEL_2",
     "3": "LABEL_3",
-    "4": "LABEL_4"
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8"
   },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
@@ -65,7 +69,11 @@
     "LABEL_1": 1,
     "LABEL_2": 2,
     "LABEL_3": 3,
-    "LABEL_4": 4
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8
   },
   "layer_norm_eps": 1e-05,
   "layerdrop": 0.1,

label_encoder.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ef72578413775b35281cd23cb205c790ca54e3220ffd3d4264ac5bf66401618
-size 387
+oid sha256:64b6954f7c1e908e23e0f621392e14c14da84254105a7cfa928932f3830d2e5e
+size 435

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:381af9f09d62497a79d0237b630945c2afbaba77bb4fa83af4a31814d604982f
-size 378305028
+oid sha256:3e253002c57e573c2a7d2c6bb92948a0532b9471527eec6e154d4b71b819e6b7
+size 378309148

model_info.txt

@@ -0,0 +1,4 @@
+model_type: hubert
+model_name: facebook/hubert-base-ls960
+num_labels: 9
+labels: aː, eː, oː, æːɪ, æːʊ, ɑɪ, ɑʊ, əʊ, ɜɪ