Training in progress, step 500

config.json

@@ -0,0 +1,108 @@
+{
+  "_name_or_path": "facebook/mms-1b-all",
+  "activation_dropout": 0.05,
+  "adapter_attn_dim": 16,
+  "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": 1024,
+  "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": 0.05,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 1280,
+  "initializer_range": 0.02,
+  "intermediate_size": 5120,
+  "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": 48,
+  "num_negatives": 100,
+  "output_hidden_size": 1280,
+  "pad_token_id": 51,
+  "proj_codevector_dim": 1024,
+  "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": "4.33.2",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 52,
+  "xvector_output_dim": 512
+}

preprocessor_config.json

@@ -0,0 +1,10 @@
+{
+  "cache_dir": "/tmp/",
+  "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:f6763bb393d7a0c00b7f46083f6a7bfce4ec07cb7668b3c5f03634ee2159e535
+size 3859242189

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token": "<s>",
+  "cache_dir": "/tmp/",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "replace_word_delimiter_char": " ",
+  "target_lang": "ara",
+  "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 sha256:05ffedd7010830f074b45f8586efacb24cf51a825f99c19403fcb287066b9637
+size 4027

vocab.json

@@ -0,0 +1,56 @@
+{
+  "ara": {
+    "+": 1,
+    ".": 2,
+    "[": 3,
+    "[PAD]": 51,
+    "[UNK]": 50,
+    "]": 4,
+    "b": 5,
+    "c": 6,
+    "e": 7,
+    "g": 8,
+    "i": 9,
+    "m": 10,
+    "o": 11,
+    "r": 12,
+    "|": 0,
+    "ء": 13,
+    "آ": 14,
+    "أ": 15,
+    "إ": 16,
+    "ا": 17,
+    "ب": 18,
+    "ة": 19,
+    "ت": 20,
+    "ث": 21,
+    "ج": 22,
+    "ح": 23,
+    "خ": 24,
+    "د": 25,
+    "ذ": 26,
+    "ر": 27,
+    "ز": 28,
+    "س": 29,
+    "ش": 30,
+    "ص": 31,
+    "ض": 32,
+    "ط": 33,
+    "ظ": 34,
+    "ع": 35,
+    "غ": 36,
+    "ف": 37,
+    "ق": 38,
+    "ك": 39,
+    "ل": 40,
+    "م": 41,
+    "ن": 42,
+    "ه": 43,
+    "و": 44,
+    "ى": 45,
+    "ي": 46,
+    "پ": 47,
+    "ڥ": 48,
+    "ڨ": 49
+  }
+}