Training in progress, step 2

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 49,
+  "<s>": 48
+}

config.json

@@ -0,0 +1,109 @@
+{
+  "_name_or_path": "classla/wav2vec2-xls-r-parlaspeech-hr",
+  "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": 768,
+  "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": 0.0,
+  "gradient_checkpointing": false,
+  "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_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": 24,
+  "num_negatives": 100,
+  "output_hidden_size": 1024,
+  "pad_token_id": 1,
+  "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": "4.31.0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 50,
+  "xvector_output_dim": 512
+}

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
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5be3ca9c03b32f06518cc5ae38f555327dc20ed67a16932c766ccbc702c1bd27
+size 1262100973

runs/Aug13_21-01-21_530b34934887/events.out.tfevents.1691960487.530b34934887.156.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9305a77eabcc1360cfa3a263622c9c23b3023882b972140243de70e3d4aa601b
+size 5496

runs/Aug13_21-18-38_530b34934887/events.out.tfevents.1691961529.530b34934887.156.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb983afbd446153dfd530b11ffa28ae356416874f4a0127b2221a308dc9d6386
+size 5491

runs/Aug13_21-20-32_530b34934887/events.out.tfevents.1691961636.530b34934887.156.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ba2f84c465eea3ded81ad1da674bd80ecf0b6d43761b4213b5b24fe849387eb
+size 5491

runs/Aug13_21-21-56_530b34934887/events.out.tfevents.1691961722.530b34934887.156.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edab27bbf3ad696e89312ea65a96bae2b94a78fdf114d6a8ce7f55567138b826
+size 5489

runs/Aug13_21-25-26_530b34934887/events.out.tfevents.1691961931.530b34934887.156.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27c2748b45e13fb8c226c8613ce75244097b4f9f4013cc066296f405b61cba21
+size 4184

runs/Aug13_21-35-34_530b34934887/events.out.tfevents.1691962539.530b34934887.9696.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b00a3a823f9929e252595d7c66667b2017487a558011b1ed6c50620031d2520
+size 5489

runs/Aug13_21-46-41_530b34934887/events.out.tfevents.1691963210.530b34934887.9696.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2462168b03a926ff6303f5a0451f3c8ebf222afb9bebd32c0f9479b1c12a1db5
+size 4184

runs/Aug13_21-52-46_530b34934887/events.out.tfevents.1691963570.530b34934887.13943.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d67760ea1b0652f27020dec1fc4eab3e34cf9992f442cdc4c2340eea41f9ef8b
+size 5801

special_tokens_map.json

@@ -0,0 +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]"
+}

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": true,
+  "do_normalize": true,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "processor_class": "Wav2Vec2Processor",
+  "replace_word_delimiter_char": " ",
+  "return_attention_mask": true,
+  "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:ea196fd8b03b9e704b8f26ff29dbb7473a707e40801f644b0c5d4189213bec19
+size 3963

vocab.json

@@ -0,0 +1,50 @@
+{
+  " ": 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
+}