Upload 10 files

config.json

@@ -0,0 +1,115 @@
+{
+  "_name_or_path": "checkpoint-1200",
+  "activation_dropout": 0.1,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 256,
+  "contrastive_logits_temperature": 0.1,
+  "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": true,
+  "diversity_loss_weight": 0.1,
+  "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,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "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",
+  "num_adapter_layers": 3,
+  "num_attention_heads": 16,
+  "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": 24,
+  "num_negatives": 100,
+  "output_hidden_size": 1024,
+  "pad_token_id": 64,
+  "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": 65,
+  "xvector_output_dim": 512
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd2f774f6cf1ca2bd300966262722c8cde7aab481aed5e40f8b70664af4d8d6c
+size 2490594117

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": true,
+  "sampling_rate": 16000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d1176a167f49d4d997324e388a10a7e83e555a32144196cecdac19812847823
+size 1262195949

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c438dbe3477c483067ae6907d5b0fdcc8f6e66c02f2ef7717fe65f4b5b65eda
+size 14575

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:573c0e110dfe1e7a3fc11065b73453594c7e0321077f7f0120dfed0a0d70518c
+size 557

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b5d8f13321c8b4e468ca80ef66eaf9552edb236f9798a14f3c7466d6f8495a4
+size 627

trainer_state.json

@@ -0,0 +1,211 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 26.395939086294415,
+  "global_step": 5200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.03,
+      "learning_rate": 0.0002,
+      "loss": 0.2479,
+      "step": 400
+    },
+    {
+      "epoch": 2.03,
+      "eval_loss": 0.47397056221961975,
+      "eval_runtime": 121.9231,
+      "eval_samples_per_second": 17.47,
+      "eval_steps_per_second": 2.19,
+      "eval_wer": 0.5506920619898261,
+      "step": 400
+    },
+    {
+      "epoch": 4.06,
+      "learning_rate": 0.00018605221657613458,
+      "loss": 0.2306,
+      "step": 800
+    },
+    {
+      "epoch": 4.06,
+      "eval_loss": 0.4647212624549866,
+      "eval_runtime": 123.4969,
+      "eval_samples_per_second": 17.247,
+      "eval_steps_per_second": 2.162,
+      "eval_wer": 0.5497456524310895,
+      "step": 800
+    },
+    {
+      "epoch": 6.09,
+      "learning_rate": 0.00017206938847029964,
+      "loss": 0.201,
+      "step": 1200
+    },
+    {
+      "epoch": 6.09,
+      "eval_loss": 0.43976637721061707,
+      "eval_runtime": 125.3202,
+      "eval_samples_per_second": 16.996,
+      "eval_steps_per_second": 2.131,
+      "eval_wer": 0.5441854962735123,
+      "step": 1200
+    },
+    {
+      "epoch": 8.12,
+      "learning_rate": 0.0001580515156824952,
+      "loss": 0.2676,
+      "step": 1600
+    },
+    {
+      "epoch": 8.12,
+      "eval_loss": 0.46590062975883484,
+      "eval_runtime": 127.6886,
+      "eval_samples_per_second": 16.681,
+      "eval_steps_per_second": 2.091,
+      "eval_wer": 0.5331834851532,
+      "step": 1600
+    },
+    {
+      "epoch": 10.15,
+      "learning_rate": 0.00014403364289469075,
+      "loss": 0.2295,
+      "step": 2000
+    },
+    {
+      "epoch": 10.15,
+      "eval_loss": 0.433741956949234,
+      "eval_runtime": 126.2574,
+      "eval_samples_per_second": 16.87,
+      "eval_steps_per_second": 2.115,
+      "eval_wer": 0.5302259552821483,
+      "step": 2000
+    },
+    {
+      "epoch": 12.18,
+      "learning_rate": 0.00013001577010688628,
+      "loss": 0.2011,
+      "step": 2400
+    },
+    {
+      "epoch": 12.18,
+      "eval_loss": 0.43763187527656555,
+      "eval_runtime": 127.2021,
+      "eval_samples_per_second": 16.745,
+      "eval_steps_per_second": 2.099,
+      "eval_wer": 0.5218265704483616,
+      "step": 2400
+    },
+    {
+      "epoch": 14.21,
+      "learning_rate": 0.00011599789731908184,
+      "loss": 0.1883,
+      "step": 2800
+    },
+    {
+      "epoch": 14.21,
+      "eval_loss": 0.4427320659160614,
+      "eval_runtime": 133.553,
+      "eval_samples_per_second": 15.949,
+      "eval_steps_per_second": 1.999,
+      "eval_wer": 0.5275050278007808,
+      "step": 2800
+    },
+    {
+      "epoch": 16.24,
+      "learning_rate": 0.00010198002453127737,
+      "loss": 0.1599,
+      "step": 3200
+    },
+    {
+      "epoch": 16.24,
+      "eval_loss": 0.4528989791870117,
+      "eval_runtime": 130.4751,
+      "eval_samples_per_second": 16.325,
+      "eval_steps_per_second": 2.046,
+      "eval_wer": 0.5167396190701526,
+      "step": 3200
+    },
+    {
+      "epoch": 18.27,
+      "learning_rate": 8.796215174347293e-05,
+      "loss": 0.1473,
+      "step": 3600
+    },
+    {
+      "epoch": 18.27,
+      "eval_loss": 0.46878582239151,
+      "eval_runtime": 130.7961,
+      "eval_samples_per_second": 16.285,
+      "eval_steps_per_second": 2.041,
+      "eval_wer": 0.5125990772506802,
+      "step": 3600
+    },
+    {
+      "epoch": 20.3,
+      "learning_rate": 7.394427895566848e-05,
+      "loss": 0.1306,
+      "step": 4000
+    },
+    {
+      "epoch": 20.3,
+      "eval_loss": 0.46525096893310547,
+      "eval_runtime": 130.9702,
+      "eval_samples_per_second": 16.263,
+      "eval_steps_per_second": 2.039,
+      "eval_wer": 0.5118892700816279,
+      "step": 4000
+    },
+    {
+      "epoch": 22.34,
+      "learning_rate": 5.9926406167864026e-05,
+      "loss": 0.1222,
+      "step": 4400
+    },
+    {
+      "epoch": 22.34,
+      "eval_loss": 0.4552956223487854,
+      "eval_runtime": 132.9038,
+      "eval_samples_per_second": 16.027,
+      "eval_steps_per_second": 2.009,
+      "eval_wer": 0.5014787649355259,
+      "step": 4400
+    },
+    {
+      "epoch": 24.37,
+      "learning_rate": 4.5908533380059577e-05,
+      "loss": 0.1097,
+      "step": 4800
+    },
+    {
+      "epoch": 24.37,
+      "eval_loss": 0.4868864417076111,
+      "eval_runtime": 128.1956,
+      "eval_samples_per_second": 16.615,
+      "eval_steps_per_second": 2.083,
+      "eval_wer": 0.5012421625458418,
+      "step": 4800
+    },
+    {
+      "epoch": 26.4,
+      "learning_rate": 3.189066059225513e-05,
+      "loss": 0.0988,
+      "step": 5200
+    },
+    {
+      "epoch": 26.4,
+      "eval_loss": 0.45241138339042664,
+      "eval_runtime": 127.9868,
+      "eval_samples_per_second": 16.642,
+      "eval_steps_per_second": 2.086,
+      "eval_wer": 0.4968650183366852,
+      "step": 5200
+    }
+  ],
+  "max_steps": 6107,
+  "num_train_epochs": 31,
+  "total_flos": 1.2361810216998281e+19,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:402a953d59f3d2c66918c47d238ae1d51eea2ac6120f7939459a514169d7a01a
+size 3003

vocab.json

@@ -0,0 +1 @@
+{"\u0627": 0, "_": 1, "\u0643": 3, "\u0646": 4, "@": 5, "\u0630": 6, "\u0656": 7, "\u0634": 8, "\u063a": 9, "\u0622": 10, "\u0635": 11, "\u064a": 12, "\u062b": 13, "n": 14, "\u062c": 15, "d": 16, "\u0626": 17, "\u0629": 18, "\u0647": 19, "\u0632": 20, "\u0639": 21, "\u0641": 22, "i": 23, "r": 24, "v": 25, "\u06b8": 26, "k": 27, "\u0650": 28, "\u0621": 29, "\u0631": 30, "s": 31, "t": 32, "\u0649": 33, "\u0640": 34, "\u2003": 35, "\u0624": 36, "\u0642": 37, "\u0636": 38, "\u0645": 39, "\u0644": 40, "\u2026": 41, "\u0637": 42, "\u062a": 43, "\u0651": 44, "c": 45, "\u0638": 46, "e": 47, "\u061f": 48, "h": 49, "\u0628": 50, "o": 51, "\u0633": 52, "a": 53, "\u062f": 54, "p": 55, "\u0623": 56, "\u0652": 57, "\n": 58, "\u062e": 59, "\u062d": 60, "\u0648": 61, "\u0625": 62, "|": 2, "[UNK]": 63, "[PAD]": 64}