Initial commit rest of the files

added_tokens.json

@@ -0,0 +1 @@
+{}

alphabet.json

@@ -0,0 +1 @@
+{"labels": ["\u00f1", "h", "p", "g", "m", "d", "-", "t", "x", "v", "'", "l", "q", "k", "w", "i", "\u00e1", "c", "b", "z", "y", "e", "u", "f", "\u00f3", "a", "−", "\u00ed", "r", "\u00fc", "\u00e9", "j", "\u00fa", "n", "s", "o", " ", "\u2047", ""], "is_bpe": false}

config.json

@@ -0,0 +1,78 @@
+{
+  "_name_or_path": "facebook/wav2vec2-xls-r-300m",
+  "activation_dropout": 0.0,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "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": true,
+  "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_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_prob": 0.05,
+  "model_type": "wav2vec2",
+  "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,
+  "pad_token_id": 34,
+  "proj_codevector_dim": 768,
+  "torch_dtype": "float32",
+  "transformers_version": "4.4.0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 35
+}

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
+}

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": null, "eos_token": null, "unk_token": "[UNK]", "pad_token": "[PAD]"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "bos_token": null, "eos_token": null, "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "tokenizer_class": "Wav2Vec2CTCTokenizer", "processor_class": "Wav2Vec2ProcessorWithLM"}

vocab.json

@@ -0,0 +1 @@
+{"ó": 0, "n": 2, "v": 3, "e": 4, "i": 5, "g": 6, "s": 7, "q": 8, "r": 9, "f": 10, "é": 11, "u": 12, "m": 13, "ú": 14, "y": 15, "í": 16, "x": 17, "c": 18, "a": 19, "w": 20, "p": 21, "ñ": 22, "t": 23, "d": 24, "k": 25, "b": 26, "j": 27, "z": 28, "á": 29, "h": 30, "o": 31, "l": 32, "|": 1, "[UNK]": 33, "[PAD]": 34}