Added Polish model

added_tokens.json

@@ -0,0 +1 @@
+{"<s>": 37, "</s>": 38}

config.json

@@ -0,0 +1,108 @@
+{
+  "_name_or_path": "facebook/wav2vec2-xls-r-300m",
+  "activation_dropout": 0.0,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.1,
+  "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": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "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": 36,
+  "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": "4.16.0.dev0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 39,
+  "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 sha256:9207e40dd155719fa2417d1c9f6b98fb40c2034307e3325e7c429cf8cf219184
+size 1262083569

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "./", "tokenizer_class": "Wav2Vec2CTCTokenizer", "processor_class": "Wav2Vec2Processor"}

trainer_state.json

@@ -0,0 +1,224 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.669540229885057,
+  "global_step": 3250,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.36,
+      "learning_rate": 4.94e-05,
+      "loss": 7.315,
+      "step": 250
+    },
+    {
+      "epoch": 0.36,
+      "eval_cer": 1.0,
+      "eval_loss": 3.364396810531616,
+      "eval_runtime": 411.3291,
+      "eval_samples_per_second": 18.839,
+      "eval_steps_per_second": 2.356,
+      "eval_wer": 1.0,
+      "step": 250
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 9.94e-05,
+      "loss": 3.2126,
+      "step": 500
+    },
+    {
+      "epoch": 0.72,
+      "eval_cer": 1.0,
+      "eval_loss": 3.178248405456543,
+      "eval_runtime": 409.0228,
+      "eval_samples_per_second": 18.945,
+      "eval_steps_per_second": 2.369,
+      "eval_wer": 1.0,
+      "step": 500
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 9.992892086330936e-05,
+      "loss": 3.1414,
+      "step": 750
+    },
+    {
+      "epoch": 1.08,
+      "eval_cer": 1.0,
+      "eval_loss": 3.1066977977752686,
+      "eval_runtime": 414.126,
+      "eval_samples_per_second": 18.712,
+      "eval_steps_per_second": 2.34,
+      "eval_wer": 1.0,
+      "step": 750
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 9.985697841726619e-05,
+      "loss": 1.9013,
+      "step": 1000
+    },
+    {
+      "epoch": 1.44,
+      "eval_cer": 0.12787848954973915,
+      "eval_loss": 0.5506780743598938,
+      "eval_runtime": 412.7461,
+      "eval_samples_per_second": 18.774,
+      "eval_steps_per_second": 2.348,
+      "eval_wer": 0.5514430132072395,
+      "step": 1000
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 9.978503597122302e-05,
+      "loss": 0.5632,
+      "step": 1250
+    },
+    {
+      "epoch": 1.8,
+      "eval_cer": 0.06747688721413134,
+      "eval_loss": 0.28180211782455444,
+      "eval_runtime": 412.6671,
+      "eval_samples_per_second": 18.778,
+      "eval_steps_per_second": 2.348,
+      "eval_wer": 0.30760729749805243,
+      "step": 1250
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 9.971309352517985e-05,
+      "loss": 0.388,
+      "step": 1500
+    },
+    {
+      "epoch": 2.16,
+      "eval_cer": 0.053711059057835714,
+      "eval_loss": 0.2308780699968338,
+      "eval_runtime": 524.2327,
+      "eval_samples_per_second": 14.782,
+      "eval_steps_per_second": 1.848,
+      "eval_wer": 0.24573799300686633,
+      "step": 1500
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 9.96411510791367e-05,
+      "loss": 0.3175,
+      "step": 1750
+    },
+    {
+      "epoch": 2.51,
+      "eval_cer": 0.0491677133901393,
+      "eval_loss": 0.2099951058626175,
+      "eval_runtime": 529.8067,
+      "eval_samples_per_second": 14.626,
+      "eval_steps_per_second": 1.829,
+      "eval_wer": 0.22468612424588294,
+      "step": 1750
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 9.956920863309353e-05,
+      "loss": 0.294,
+      "step": 2000
+    },
+    {
+      "epoch": 2.87,
+      "eval_cer": 0.046197281913749985,
+      "eval_loss": 0.19443732500076294,
+      "eval_runtime": 533.3896,
+      "eval_samples_per_second": 14.528,
+      "eval_steps_per_second": 1.817,
+      "eval_wer": 0.21001141366378606,
+      "step": 2000
+    },
+    {
+      "epoch": 3.23,
+      "learning_rate": 9.949726618705036e-05,
+      "loss": 0.2543,
+      "step": 2250
+    },
+    {
+      "epoch": 3.23,
+      "eval_cer": 0.04413495377442826,
+      "eval_loss": 0.19428253173828125,
+      "eval_runtime": 534.1775,
+      "eval_samples_per_second": 14.506,
+      "eval_steps_per_second": 1.814,
+      "eval_wer": 0.19475696142906318,
+      "step": 2250
+    },
+    {
+      "epoch": 3.59,
+      "learning_rate": 9.94253237410072e-05,
+      "loss": 0.2493,
+      "step": 2500
+    },
+    {
+      "epoch": 3.59,
+      "eval_cer": 0.04232723404736848,
+      "eval_loss": 0.1892683357000351,
+      "eval_runtime": 528.5117,
+      "eval_samples_per_second": 14.662,
+      "eval_steps_per_second": 1.833,
+      "eval_wer": 0.18792688008406255,
+      "step": 2500
+    },
+    {
+      "epoch": 3.95,
+      "learning_rate": 9.935338129496404e-05,
+      "loss": 0.2333,
+      "step": 2750
+    },
+    {
+      "epoch": 3.95,
+      "eval_cer": 0.04126919464530219,
+      "eval_loss": 0.1779049038887024,
+      "eval_runtime": 417.6945,
+      "eval_samples_per_second": 18.552,
+      "eval_steps_per_second": 2.32,
+      "eval_wer": 0.18323459608312045,
+      "step": 2750
+    },
+    {
+      "epoch": 4.31,
+      "learning_rate": 9.928143884892087e-05,
+      "loss": 0.2131,
+      "step": 3000
+    },
+    {
+      "epoch": 4.31,
+      "eval_cer": 0.040952348621153996,
+      "eval_loss": 0.18109484016895294,
+      "eval_runtime": 409.5311,
+      "eval_samples_per_second": 18.922,
+      "eval_steps_per_second": 2.366,
+      "eval_wer": 0.17970179538743047,
+      "step": 3000
+    },
+    {
+      "epoch": 4.67,
+      "learning_rate": 9.92094964028777e-05,
+      "loss": 0.1992,
+      "step": 3250
+    },
+    {
+      "epoch": 4.67,
+      "eval_cer": 0.03845435719862851,
+      "eval_loss": 0.17126505076885223,
+      "eval_runtime": 422.692,
+      "eval_samples_per_second": 18.332,
+      "eval_steps_per_second": 2.292,
+      "eval_wer": 0.169665018026342,
+      "step": 3250
+    }
+  ],
+  "max_steps": 348000,
+  "num_train_epochs": 500,
+  "total_flos": 1.643409928882224e+19,
+  "trial_name": null,
+  "trial_params": null
+}

vocab.json

@@ -0,0 +1 @@
+{"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, "ó": 27, "č": 28, "ł": 29, "ń": 30, "ś": 31, "š": 32, "ź": 33, "ż": 34, "|": 0, "[UNK]": 35, "[PAD]": 36}