Training in progress, epoch 0

config.json

@@ -0,0 +1,190 @@
+{
+  "_name_or_path": "jonatasgrosman/wav2vec2-large-xlsr-53-arabic",
+  "activation_dropout": 0.05,
+  "adapter_attn_dim": null,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "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": 0.05,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.05,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "faa",
+    "1": "duad",
+    "10": "quaf",
+    "11": "suad",
+    "12": "haa",
+    "13": "sa",
+    "14": "jeem",
+    "15": "yaa",
+    "16": "tua",
+    "17": "laam",
+    "18": "seen",
+    "19": "zua",
+    "2": "kha",
+    "20": "saud",
+    "21": "meem",
+    "22": "ta",
+    "23": "aain",
+    "24": "alif",
+    "25": "hha",
+    "26": "za",
+    "27": "wao",
+    "28": "ba",
+    "29": "dal",
+    "3": "zaa",
+    "30": "sheen",
+    "31": "qauf",
+    "32": "waow",
+    "33": "lam",
+    "34": "zuad",
+    "4": "ghain",
+    "5": "kaif",
+    "6": "noon",
+    "7": "raa",
+    "8": "zhal",
+    "9": "hamzah"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "aain": "23",
+    "alif": "24",
+    "ba": "28",
+    "dal": "29",
+    "duad": "1",
+    "faa": "0",
+    "ghain": "4",
+    "haa": "12",
+    "hamzah": "9",
+    "hha": "25",
+    "jeem": "14",
+    "kaif": "5",
+    "kha": "2",
+    "laam": "17",
+    "lam": "33",
+    "meem": "21",
+    "noon": "6",
+    "qauf": "31",
+    "quaf": "10",
+    "raa": "7",
+    "sa": "13",
+    "saud": "20",
+    "seen": "18",
+    "sheen": "30",
+    "suad": "11",
+    "ta": "22",
+    "tua": "16",
+    "wao": "27",
+    "waow": "32",
+    "yaa": "15",
+    "za": "26",
+    "zaa": "3",
+    "zhal": "8",
+    "zua": "19",
+    "zuad": "34"
+  },
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.05,
+  "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": 0,
+  "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": "4.35.0.dev0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51,
+  "xvector_output_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac029033209327c9c57f079c8a9b777c31021302795462bd0732d43430a4f66d
+size 1262893236

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
+}

runs/Nov02_17-49-02_5d326aa6cc2b/events.out.tfevents.1698947348.5d326aa6cc2b.23062.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f40ac767b9294c064ac43dbdcc9a8d5dc1ee6e9a7a41ee3ceef9ed5a0684df26
+size 7680

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a58930bfcf1279a10cbe902b4afee3e840f9ce4f0ffe3a7f63e286682ba8af5f
+size 4664