add tokenizer

checkpoint-1000/config.json

@@ -0,0 +1,117 @@
+{
+  "_name_or_path": "wav2vec2-model1-torgo",
+  "activation_dropout": 0.0,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "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": "mean",
+  "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,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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": 29,
+  "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": "4.17.0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32,
+  "xvector_output_dim": 512
+}

checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61d83187a1f813e570b8172202be132f9dc0f940a837641665703d14c5c904da
+size 721679569

checkpoint-1000/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
+}

checkpoint-1000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:973e9ac78b4070bbd43cb3872ccb15ad0f51d66f21e401675a74eb6c00746104
+size 377668631

checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:918497def91b863e016b56685d7531de6045252ca14b1119353f10edbdd07d05
+size 14567

checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb3c2d4cc9cd5db0ded821257afbbb9e216de72b23cbfad8f7530e40d4a66085
+size 623

checkpoint-1000/trainer_state.json

@@ -0,0 +1,46 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.526315789473684,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.005,
+      "loss": 12.1146,
+      "step": 500
+    },
+    {
+      "epoch": 0.76,
+      "eval_loss": 6.7651519775390625,
+      "eval_runtime": 549.3202,
+      "eval_samples_per_second": 0.843,
+      "eval_steps_per_second": 0.106,
+      "eval_wer": 1.0,
+      "step": 500
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 0.01,
+      "loss": 3.7548,
+      "step": 1000
+    },
+    {
+      "epoch": 1.53,
+      "eval_loss": 4.368209362030029,
+      "eval_runtime": 514.3478,
+      "eval_samples_per_second": 0.9,
+      "eval_steps_per_second": 0.113,
+      "eval_wer": 1.0,
+      "step": 1000
+    }
+  ],
+  "max_steps": 19650,
+  "num_train_epochs": 30,
+  "total_flos": 1.3443902730745056e+17,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5090d2459c36fef37ff5438732de6290998bb02855c3984b89a4e1df893aa0c3
+size 2991

runs/Apr08_13-08-44_TUF/1649448589.3046203/events.out.tfevents.1649448589.TUF.22816.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32fd0b7ebd98d7e0bc02e69bf806503d83685e71c76ac90b291cfc73ba798160
+size 4782

runs/Apr08_13-08-44_TUF/events.out.tfevents.1649448589.TUF.22816.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0fdb926de3a9617266f7832117e9f41ddd14a50b72274d5b611b450b71cfec8
+size 5963

vocab.json

@@ -1 +1 @@
-{"s": 0, "v": 1, "l": 2, "o": 3, "u": 4, "n": 5, "w": 6, "g": 7, "'": 8, "t": 9, "a": 10, "z": 11, "d": 12, "e": 14, "i": 15, "j": 16, "h": 17, "q": 18, "f": 19, "k": 20, "c": 21, "m": 22, "x": 23, "y": 24, "b": 25, "r": 26, "p": 27, "[UNK]": 28, "[PAD]": 29, "|": 13}
+{"z": 0, "l": 1, "t": 2, "e": 3, "c": 4, "w": 5, "i": 6, "g": 7, "d": 8, "r": 9, "j": 10, "y": 12, "p": 13, "m": 14, "h": 15, "k": 16, "f": 17, "a": 18, "'": 19, "q": 20, "x": 21, "o": 22, "u": 23, "v": 24, "n": 25, "s": 26, "b": 27, "[UNK]": 28, "[PAD]": 29, "|": 11}