Initial commit

config.json

@@ -0,0 +1,115 @@
+{
+  "_name_or_path": "wietsedv/wav2vec2-large-xlsr-53-frisian",
+  "activation_dropout": 0.1,
+  "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": 256,
+  "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,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "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": 2,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.004,
+  "mask_time_length": 2,
+  "mask_time_min_masks": 2,
+  "mask_time_min_space": 1,
+  "mask_time_other": 0.0,
+  "mask_time_prob": 0.065,
+  "mask_time_selection": "static",
+  "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": 0,
+  "proj_codevector_dim": 256,
+  "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": "4.18.0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 93,
+  "xvector_output_dim": 512
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aed6c40df5bcb492e2fd185daa3ee50bd1b4fb9938ec51e362dc37c3a535463e
+size 2524519073

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:c501785a780f4f67bd6778c56cfd6b0268a5dfc758816e2bd47310cce1c5def7
+size 1262279985

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c47a85f9d4ee5cb1d3978d7d94b8ce976a0ac1b46a7e150096835bd8c2af1b9
+size 14503

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:116e75a6e0782fc1aa30a859398112b712e8c5e6df45b54ea7049a867cdeb980
+size 559

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:459e368945a77e0055d06319cbeb3cb87a3c2d81ef0f4fee4d016e96366afcfa
+size 623

special_tokens_map.json

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

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": "|", "replace_word_delimiter_char": " ", "tokenizer_class": "Wav2Vec2CTCTokenizer", "processor_class": "Wav2Vec2Processor"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec36c8956da1b198ac266ba13c356186ea94aef8f97e83e7116071cdd4a52b4f
+size 3055

vocab.json

@@ -0,0 +1 @@
+{"<pad>": 0, "<s>": 1, "</s>": 2, "|": 4, "a": 5, "b": 6, "c": 7, "d": 8, "e": 9, "f": 10, "g": 11, "h": 12, "i": 13, "j": 14, "k": 15, "l": 16, "m": 17, "n": 18, "o": 19, "p": 20, "q": 21, "r": 22, "s": 23, "t": 24, "u": 25, "v": 26, "w": 27, "x": 28, "y": 29, "z": 30, "à": 31, "á": 32, "â": 33, "ä": 34, "è": 35, "é": 36, "ê": 37, "ë": 38, "ï": 39, "ô": 40, "ú": 41, "û": 42, "ü": 43, "O": 44, "\t": 45, "Ć": 46, "T": 47, "-": 48, "A": 49, "P": 50, "H": 51, "Ê": 52, "Ë": 53, "V": 54, "C": 55, "Ç": 56, "Z": 57, "U": 58, "Ü": 59, "I": 60, "R": 61, "K": 62, "'": 63, "M": 64, "Y": 65, "Â": 66, "Ú": 67, "Ô": 68, "F": 69, " ": 70, "N": 71, "Ö": 72, "E": 73, "J": 74, "Á": 75, "Û": 76, "S": 77, "Q": 78, "Ä": 79, "[": 80, "Č": 81, "É": 82, "W": 83, "X": 84, "L": 85, "B": 86, "À": 87, "": 88, "Ï": 89, "G": 90, "È": 91, "D": 92, "[UNK]": 3}