Training in progress, step 2

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "facebook/wav2vec2-base",
+  "_name_or_path": "classla/wav2vec2-xls-r-parlaspeech-hr",
   "activation_dropout": 0.0,
   "adapter_attn_dim": null,
   "adapter_kernel_size": 3,
@@ -9,12 +9,12 @@
   "architectures": [
     "Wav2Vec2ForCTC"
   ],
-  "attention_dropout": 0.1,
+  "attention_dropout": 0.0,
   "bos_token_id": 1,
   "classifier_proj_size": 256,
-  "codevector_dim": 256,
+  "codevector_dim": 768,
   "contrastive_logits_temperature": 0.1,
-  "conv_bias": false,
+  "conv_bias": true,
   "conv_dim": [
     512,
     512,
@@ -45,50 +45,41 @@
   "ctc_loss_reduction": "mean",
   "ctc_zero_infinity": false,
   "diversity_loss_weight": 0.1,
-  "do_stable_layer_norm": false,
+  "do_stable_layer_norm": true,
   "eos_token_id": 2,
   "feat_extract_activation": "gelu",
-  "feat_extract_norm": "group",
-  "feat_proj_dropout": 0.1,
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "layer",
+  "feat_proj_dropout": 0.0,
   "feat_quantizer_dropout": 0.0,
   "final_dropout": 0.0,
-  "freeze_feat_extract_train": true,
+  "gradient_checkpointing": false,
   "hidden_act": "gelu",
-  "hidden_dropout": 0.1,
-  "hidden_size": 768,
+  "hidden_dropout": 0.0,
+  "hidden_size": 1024,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "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",
-  "no_mask_channel_overlap": false,
-  "no_mask_time_overlap": false,
   "num_adapter_layers": 3,
-  "num_attention_heads": 12,
+  "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": 12,
+  "num_hidden_layers": 24,
   "num_negatives": 100,
-  "output_hidden_size": 768,
-  "pad_token_id": 0,
-  "proj_codevector_dim": 256,
+  "output_hidden_size": 1024,
+  "pad_token_id": 1,
+  "proj_codevector_dim": 768,
   "tdnn_dilation": [
     1,
     2,
@@ -113,6 +104,6 @@
   "torch_dtype": "float32",
   "transformers_version": "4.31.0",
   "use_weighted_layer_sum": false,
-  "vocab_size": 32,
+  "vocab_size": 50,
   "xvector_output_dim": 512
 }

preprocessor_config.json

@@ -5,6 +5,6 @@
   "padding_side": "right",
   "padding_value": 0.0,
   "processor_class": "Wav2Vec2Processor",
-  "return_attention_mask": false,
+  "return_attention_mask": true,
   "sampling_rate": 16000
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c63ed9577e7ec18b118ec0582a3a27ffdf656c3f16ec9b5795017e8cd25f6f45
-size 377655777
+oid sha256:4ba0070d0c62b2f6369c011b53da137b9cb9a054d5e5729da2b6a75de8c7b015
+size 1262100973

runs/Aug16_22-57-24_ad9991e891e0/events.out.tfevents.1692226648.ad9991e891e0.188.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff21914eb309e2df3b826e415188efe952d3b6ae70cd74c3f622e7c3aeda7ddc
+size 6264

special_tokens_map.json

@@ -1,6 +1,22 @@
 {
+  "additional_special_tokens": [
+    {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
   "bos_token": "<s>",
   "eos_token": "</s>",
-  "pad_token": "<pad>",
-  "unk_token": "<unk>"
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]"
 }

tokenizer_config.json

@@ -1,16 +1,16 @@
 {
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
-  "do_lower_case": false,
+  "do_lower_case": true,
   "do_normalize": true,
   "eos_token": "</s>",
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<pad>",
+  "pad_token": "[PAD]",
   "processor_class": "Wav2Vec2Processor",
   "replace_word_delimiter_char": " ",
-  "return_attention_mask": false,
+  "return_attention_mask": true,
   "target_lang": null,
   "tokenizer_class": "Wav2Vec2CTCTokenizer",
-  "unk_token": "<unk>",
+  "unk_token": "[UNK]",
   "word_delimiter_token": "|"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7605dd591aaa7fb4ca67db3970dbdd0409cef778f0c2d89ff60642e9a9ab4fd
+oid sha256:028821aa33b99b8f220817932a2fcda87dc1fc670e081a172ee10bdfecfc3401
 size 3963

vocab.json

@@ -1,34 +1,50 @@
 {
-  "'": 27,
-  "</s>": 2,
-  "<pad>": 0,
-  "<s>": 1,
-  "<unk>": 3,
-  "A": 7,
-  "B": 24,
-  "C": 19,
-  "D": 14,
-  "E": 5,
-  "F": 20,
-  "G": 21,
-  "H": 11,
-  "I": 10,
-  "J": 29,
-  "K": 26,
-  "L": 15,
-  "M": 17,
-  "N": 9,
-  "O": 8,
-  "P": 23,
-  "Q": 30,
-  "R": 13,
-  "S": 12,
-  "T": 6,
-  "U": 16,
-  "V": 25,
-  "W": 18,
-  "X": 28,
-  "Y": 22,
-  "Z": 31,
-  "|": 4
+  " ": 0,
+  ".": 47,
+  "0": 46,
+  "1": 37,
+  "2": 38,
+  "3": 39,
+  "4": 40,
+  "5": 41,
+  "6": 42,
+  "7": 43,
+  "8": 44,
+  "9": 45,
+  "[PAD]": 1,
+  "[UNK]": 2,
+  "a": 3,
+  "b": 4,
+  "c": 5,
+  "d": 6,
+  "e": 7,
+  "f": 8,
+  "g": 9,
+  "h": 10,
+  "i": 11,
+  "j": 12,
+  "k": 13,
+  "l": 14,
+  "m": 15,
+  "n": 16,
+  "o": 17,
+  "p": 18,
+  "q": 19,
+  "r": 20,
+  "s": 21,
+  "t": 22,
+  "u": 23,
+  "v": 24,
+  "w": 25,
+  "x": 26,
+  "y": 27,
+  "z": 28,
+  "ä": 29,
+  "ü": 30,
+  "ć": 31,
+  "č": 32,
+  "đ": 33,
+  "š": 34,
+  "ž": 35,
+  "ӧ": 36
 }