Training in progress, step 400

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 94,
+  "<s>": 93
+}

config.json

@@ -0,0 +1,116 @@
+{
+  "_name_or_path": "jonatasgrosman/wav2vec2-large-xlsr-53-arabic",
+  "activation_dropout": 0.0,
+  "adapter_attn_dim": null,
+  "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": 92,
+  "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": "4.36.0.dev0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 95,
+  "xvector_output_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9407f07671a0ccf437b3ca95d19b9ce0d85285734389a93b976afb998a5a1fdd
+size 1262196980

preprocessor_config.json

@@ -0,0 +1,10 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "Wav2Vec2Processor",
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

runs/Dec06_08-18-09_8e777a613ead/events.out.tfevents.1701851114.8e777a613ead.15517.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79e221e3aa8856476107a091be5f42ecc500b07b980e6d1a8444199271b9402a
+size 7311

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,48 @@
+{
+  "added_tokens_decoder": {
+    "91": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "92": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "93": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "94": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "processor_class": "Wav2Vec2Processor",
+  "replace_word_delimiter_char": " ",
+  "target_lang": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6043807b88687b1d97a0c25c9482a6207b2808ee9de2175e58b1ca0d334e059b
+size 4728

vocab.json

@@ -0,0 +1,95 @@
+{
+  "[PAD]": 92,
+  "[UNK]": 91,
+  "_": 1,
+  "a": 2,
+  "b": 3,
+  "c": 4,
+  "d": 5,
+  "e": 6,
+  "f": 7,
+  "g": 8,
+  "h": 9,
+  "i": 10,
+  "j": 11,
+  "k": 12,
+  "l": 13,
+  "m": 14,
+  "n": 15,
+  "o": 16,
+  "p": 17,
+  "q": 18,
+  "r": 19,
+  "s": 20,
+  "t": 21,
+  "u": 22,
+  "v": 23,
+  "w": 24,
+  "x": 25,
+  "y": 26,
+  "|": 0,
+  "«": 27,
+  "»": 28,
+  "؛": 29,
+  "ء": 30,
+  "آ": 31,
+  "أ": 32,
+  "ؤ": 33,
+  "إ": 34,
+  "ئ": 35,
+  "ا": 36,
+  "ب": 37,
+  "ة": 38,
+  "ت": 39,
+  "ث": 40,
+  "ج": 41,
+  "ح": 42,
+  "خ": 43,
+  "د": 44,
+  "ذ": 45,
+  "ر": 46,
+  "ز": 47,
+  "س": 48,
+  "ش": 49,
+  "ص": 50,
+  "ض": 51,
+  "ط": 52,
+  "ظ": 53,
+  "ع": 54,
+  "غ": 55,
+  "ـ": 56,
+  "ف": 57,
+  "ق": 58,
+  "ك": 59,
+  "ل": 60,
+  "م": 61,
+  "ن": 62,
+  "ه": 63,
+  "و": 64,
+  "ى": 65,
+  "ي": 66,
+  "ً": 67,
+  "ٌ": 68,
+  "ٍ": 69,
+  "َ": 70,
+  "ُ": 71,
+  "ِ": 72,
+  "ّ": 73,
+  "ْ": 74,
+  "ٰ": 75,
+  "چ": 76,
+  "ڨ": 77,
+  "ک": 78,
+  "ھ": 79,
+  "ی": 80,
+  "ۖ": 81,
+  "ۗ": 82,
+  "ۘ": 83,
+  "ۚ": 84,
+  "ۛ": 85,
+  "—": 86,
+  "…": 87,
+  "☭": 88,
+  "ﺃ": 89,
+  "ﻻ": 90
+}