Training in progress, step 100

.gitignore

@@ -0,0 +1,3 @@
+checkpoint-*
+km_kh*
+.ipynb_checkpoints

config.json

@@ -0,0 +1,108 @@
+{
+  "_name_or_path": "facebook/wav2vec2-xls-r-300m",
+  "activation_dropout": 0.0,
+  "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": 768,
+  "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": false,
+  "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,
+  "gradient_checkpointing": false,
+  "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_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": 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": 73,
+  "proj_codevector_dim": 768,
+  "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.dev0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 75,
+  "xvector_output_dim": 512
+}

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:de338e5c1afe8724c486f34b78be6997d34259229acda73ba51b26c8c304a4d7
+size 1262231153

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f53351c36f9166d72fba05a26550d456156793a4caab264b38fc1e6437cf34a8
+size 2991

vocab.json

@@ -0,0 +1 @@
+{"\u1780": 1, "\u1781": 2, "\u1782": 3, "\u1783": 4, "\u1784": 5, "\u1785": 6, "\u1786": 7, "\u1787": 8, "\u1788": 9, "\u1789": 10, "\u178a": 11, "\u178b": 12, "\u178c": 13, "\u178d": 14, "\u178e": 15, "\u178f": 16, "\u1790": 17, "\u1791": 18, "\u1792": 19, "\u1793": 20, "\u1794": 21, "\u1795": 22, "\u1796": 23, "\u1797": 24, "\u1798": 25, "\u1799": 26, "\u179a": 27, "\u179b": 28, "\u179c": 29, "\u179f": 30, "\u17a0": 31, "\u17a1": 32, "\u17a2": 33, "\u17a5": 34, "\u17a7": 35, "\u17aa": 36, "\u17ab": 37, "\u17ac": 38, "\u17ad": 39, "\u17ae": 40, "\u17af": 41, "\u17b1": 42, "\u17b6": 43, "\u17b7": 44, "\u17b8": 45, "\u17b9": 46, "\u17ba": 47, "\u17bb": 48, "\u17bc": 49, "\u17bd": 50, "\u17be": 51, "\u17bf": 52, "\u17c0": 53, "\u17c1": 54, "\u17c2": 55, "\u17c3": 56, "\u17c4": 57, "\u17c5": 58, "\u17c6": 59, "\u17c7": 60, "\u17c8": 61, "\u17c9": 62, "\u17ca": 63, "\u17cb": 64, "\u17cc": 65, "\u17cd": 66, "\u17ce": 67, "\u17cf": 68, "\u17d0": 69, "\u17d2": 70, "|": 0, "[UNK]": 72, "[PAD]": 73}