updated the model

config.json

@@ -1,14 +1,11 @@
 {
-  "_name_or_path": "indonesian-nlp/wav2vec2-luganda",
-  "activation_dropout": 0.1,
-  "adapter_kernel_size": 3,
-  "adapter_stride": 2,
-  "add_adapter": false,
+  "_name_or_path": "/workspace/output_models/wav2vec2-common_voice-lg-tvoi-2",
+  "activation_dropout": 0.055,
   "apply_spec_augment": true,
   "architectures": [
     "Wav2Vec2ForCTC"
   ],
-  "attention_dropout": 0.0,
+  "attention_dropout": 0.094,
   "bos_token_id": 1,
   "classifier_proj_size": 256,
   "codevector_dim": 768,
@@ -49,32 +46,30 @@
   "feat_extract_activation": "gelu",
   "feat_extract_dropout": 0.0,
   "feat_extract_norm": "layer",
-  "feat_proj_dropout": 0.0,
+  "feat_proj_dropout": 0.04,
   "feat_quantizer_dropout": 0.0,
   "final_dropout": 0.0,
+  "gradient_checkpointing": false,
   "hidden_act": "gelu",
-  "hidden_dropout": 0.0,
+  "hidden_dropout": 0.047,
   "hidden_size": 1024,
   "initializer_range": 0.02,
   "intermediate_size": 4096,
   "layer_norm_eps": 1e-05,
-  "layerdrop": 0.0,
+  "layerdrop": 0.041,
   "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": 64,
-  "mask_feature_min_masks": 0,
-  "mask_feature_prob": 0.25,
+  "mask_feature_length": 10,
+  "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": 0.4,
   "mask_time_selection": "static",
   "model_type": "wav2vec2",
-  "num_adapter_layers": 3,
   "num_attention_heads": 16,
   "num_codevector_groups": 2,
   "num_codevectors_per_group": 320,
@@ -83,33 +78,10 @@
   "num_feat_extract_layers": 7,
   "num_hidden_layers": 24,
   "num_negatives": 100,
-  "output_hidden_size": 1024,
   "pad_token_id": 28,
   "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",
+  "transformers_version": "4.11.2",
   "use_weighted_layer_sum": false,
-  "vocab_size": 29,
-  "xvector_output_dim": 512
+  "vocab_size": 29
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0aff8a4703a7e6506993a449bf58551b3300d38e6a314c673a6e745d0b5c48d8
+oid sha256:447bf4c640af086f70af1eaeca3850c694f9d56aa085922fd02839673b611805
 size 1262042545

special_tokens_map.json

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

tokenizer_config.json

@@ -1 +1 @@
-{"unk_token": "[UNK]", "bos_token": null, "eos_token": null, "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "./", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
+{"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

vocab.json

@@ -1 +1 @@
-{"-": 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, "r": 18, "s": 19, "t": 20, "u": 21, "v": 22, "w": 23, "x": 24, "y": 25, "z": 26, "|": 0, "[UNK]": 27, "[PAD]": 28}
+{"a": 1, "b": 2, "c": 3, "d": 4, "e": 5, "f": 6, "g": 7, "h": 8, "i": 9, "j": 10, "k": 11, "l": 12, "m": 13, "n": 14, "o": 15, "p": 16, "q": 17, "r": 18, "s": 19, "t": 20, "u": 21, "v": 22, "w": 23, "x": 24, "y": 25, "z": 26, "|": 0, "[UNK]": 27, "[PAD]": 28}