Update from bmoell

README.md

@@ -0,0 +1 @@
+hello

config.json

@@ -0,0 +1,76 @@
+{
+  "_name_or_path": "facebook/wav2vec2-large-xlsr-53",
+  "activation_dropout": 0.0,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "conv_bias": true,
+  "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,
+  "do_stable_layer_norm": true,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "layer",
+  "feat_proj_dropout": 0.0,
+  "final_dropout": 0.0,
+  "gradient_checkpointing": true,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "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_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_space": 1,
+  "mask_time_other": 0.0,
+  "mask_time_prob": 0.05,
+  "mask_time_selection": "static",
+  "model_type": "wav2vec2",
+  "num_attention_heads": 16,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 24,
+  "pad_token_id": 35,
+  "transformers_version": "4.5.0.dev0",
+  "vocab_size": 36
+}

preprocessor_config.json

@@ -0,0 +1,8 @@
+{
+  "do_normalize": true,
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33ba70255aba7f19f7b47282f6fddf955c5d806385f0c6ddd5d272f8047e08b7
+size 1262081431

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9bbc82e010b07e3d0769df021d0e1c9fcab2f01ab88bf1c5bc19dc4beb3f814
+size 623

trainer_state.json

@@ -0,0 +1,184 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 28.06997084548105,
+  "global_step": 4800,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.34,
+      "learning_rate": 0.00023999999999999998,
+      "loss": 4.1009,
+      "step": 400
+    },
+    {
+      "epoch": 2.34,
+      "eval_loss": 2.947835922241211,
+      "eval_runtime": 361.2993,
+      "eval_samples_per_second": 6.944,
+      "eval_wer": 1.0,
+      "step": 400
+    },
+    {
+      "epoch": 4.68,
+      "learning_rate": 0.0002805615550755939,
+      "loss": 2.0411,
+      "step": 800
+    },
+    {
+      "epoch": 4.68,
+      "eval_loss": 0.5171445608139038,
+      "eval_runtime": 364.5526,
+      "eval_samples_per_second": 6.882,
+      "eval_wer": 0.7113982218374346,
+      "step": 800
+    },
+    {
+      "epoch": 7.02,
+      "learning_rate": 0.0002546436285097192,
+      "loss": 0.4401,
+      "step": 1200
+    },
+    {
+      "epoch": 7.02,
+      "eval_loss": 0.3676733076572418,
+      "eval_runtime": 366.7629,
+      "eval_samples_per_second": 6.841,
+      "eval_wer": 0.5746395391428857,
+      "step": 1200
+    },
+    {
+      "epoch": 9.36,
+      "learning_rate": 0.00022872570194384448,
+      "loss": 0.2829,
+      "step": 1600
+    },
+    {
+      "epoch": 9.36,
+      "eval_loss": 0.3323122262954712,
+      "eval_runtime": 371.0751,
+      "eval_samples_per_second": 6.761,
+      "eval_wer": 0.5098065332489761,
+      "step": 1600
+    },
+    {
+      "epoch": 11.69,
+      "learning_rate": 0.00020280777537796973,
+      "loss": 0.2019,
+      "step": 2000
+    },
+    {
+      "epoch": 11.69,
+      "eval_loss": 0.3595321476459503,
+      "eval_runtime": 359.0792,
+      "eval_samples_per_second": 6.987,
+      "eval_wer": 0.483899970030968,
+      "step": 2000
+    },
+    {
+      "epoch": 14.03,
+      "learning_rate": 0.00017688984881209503,
+      "loss": 0.1641,
+      "step": 2400
+    },
+    {
+      "epoch": 14.03,
+      "eval_loss": 0.38239890336990356,
+      "eval_runtime": 369.6977,
+      "eval_samples_per_second": 6.787,
+      "eval_wer": 0.4745096733375512,
+      "step": 2400
+    },
+    {
+      "epoch": 16.37,
+      "learning_rate": 0.00015097192224622027,
+      "loss": 0.1311,
+      "step": 2800
+    },
+    {
+      "epoch": 16.37,
+      "eval_loss": 0.3804999887943268,
+      "eval_runtime": 365.1667,
+      "eval_samples_per_second": 6.871,
+      "eval_wer": 0.46205587559521827,
+      "step": 2800
+    },
+    {
+      "epoch": 18.71,
+      "learning_rate": 0.00012505399568034557,
+      "loss": 0.1157,
+      "step": 3200
+    },
+    {
+      "epoch": 18.71,
+      "eval_loss": 0.39201927185058594,
+      "eval_runtime": 362.8973,
+      "eval_samples_per_second": 6.914,
+      "eval_wer": 0.4496686757017748,
+      "step": 3200
+    },
+    {
+      "epoch": 21.05,
+      "learning_rate": 9.913606911447084e-05,
+      "loss": 0.0989,
+      "step": 3600
+    },
+    {
+      "epoch": 21.05,
+      "eval_loss": 0.41990572214126587,
+      "eval_runtime": 358.4193,
+      "eval_samples_per_second": 7.0,
+      "eval_wer": 0.45106723052845393,
+      "step": 3600
+    },
+    {
+      "epoch": 23.39,
+      "learning_rate": 7.32181425485961e-05,
+      "loss": 0.0895,
+      "step": 4000
+    },
+    {
+      "epoch": 23.39,
+      "eval_loss": 0.409751832485199,
+      "eval_runtime": 369.3102,
+      "eval_samples_per_second": 6.794,
+      "eval_wer": 0.4471046585195298,
+      "step": 4000
+    },
+    {
+      "epoch": 25.73,
+      "learning_rate": 4.7300215982721384e-05,
+      "loss": 0.081,
+      "step": 4400
+    },
+    {
+      "epoch": 25.73,
+      "eval_loss": 0.41373974084854126,
+      "eval_runtime": 371.7326,
+      "eval_samples_per_second": 6.749,
+      "eval_wer": 0.4345176650794179,
+      "step": 4400
+    },
+    {
+      "epoch": 28.07,
+      "learning_rate": 2.1382289416846652e-05,
+      "loss": 0.0761,
+      "step": 4800
+    },
+    {
+      "epoch": 28.07,
+      "eval_loss": 0.4309007227420807,
+      "eval_runtime": 384.4679,
+      "eval_samples_per_second": 6.526,
+      "eval_wer": 0.4348506543238653,
+      "step": 4800
+    }
+  ],
+  "max_steps": 5130,
+  "num_train_epochs": 30,
+  "total_flos": 3.173501973340016e+19,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:689423c5378f16c9ae4472e03e9801695abb3d73c289732696e7a13880264912
+size 2287

vocab.json

@@ -0,0 +1 @@
+{"w": 0, "d": 1, "q": 2, "v": 3, "z": 4, "l": 5, "g": 6, "õ": 7, "ž": 8, "a": 10, "ä": 11, "n": 12, "ö": 13, "x": 14, "c": 15, "j": 16, "e": 17, "o": 18, "b": 19, "š": 20, "r": 21, "t": 22, "f": 23, "h": 24, "s": 25, "y": 26, "i": 27, "m": 28, "'": 29, "u": 30, "ü": 31, "p": 32, "k": 33, "|": 9, "[UNK]": 34, "[PAD]": 35}