Add catalan checkpoint epoch 2.25

config.json

@@ -0,0 +1,76 @@
+{
+  "_name_or_path": "/workspace/output_models/ca/wav2vec2-large-xlsr-catalan/checkpoint-18800",
+  "activation_dropout": 0.1,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 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,
+  "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,
+  "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_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_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_space": 1,
+  "mask_time_other": 0.0,
+  "mask_time_prob": 0.05,
+  "mask_time_selection": "static",
+  "model_type": "wav2vec2",
+  "num_attention_heads": 16,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 24,
+  "pad_token_id": 84,
+  "transformers_version": "4.5.0.dev0",
+  "vocab_size": 85
+}

preprocessor_config.json

@@ -0,0 +1,8 @@
+{
+  "do_normalize": true,
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a88f5e3965329e84300aab0b251bc1acb28aa346670666bdc9aaf8823f1b96b1
+size 1262282327

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": "|"}

vocab.json

@@ -0,0 +1 @@
+{"é": 0, "j": 1, "*": 2, "c": 3, "ä": 4, "ú": 5, "a": 6, "e": 7, "ž": 8, "ř": 9, "+": 10, "–": 11, "ὑ": 12, "u": 13, "i": 14, "x": 15, "o": 16, "“": 17, "š": 18, "ং": 19, "ı": 20, "b": 21, "ℤ": 22, "z": 23, "»": 24, "ō": 25, "w": 26, "ô": 27, "m": 28, "°": 29, "ã": 30, "f": 31, "ó": 32, "ç": 33, "ò": 35, "¡": 36, "d": 37, "…": 38, "y": 39, "g": 40, "p": 41, "¿": 42, "ö": 43, "'": 44, "ţ": 45, "·": 46, "@": 47, "ł": 48, "ş": 49, "č": 50, "ð": 51, "~": 52, "è": 53, "ì": 54, "’": 55, "ï": 56, "s": 57, "h": 58, "ň": 59, "«": 60, "t": 61, "”": 62, "å": 63, "ñ": 64, "í": 65, "ঃ": 66, "à": 67, "v": 68, "ü": 69, "ė": 70, "q": 71, "á": 72, "n": 73, "ū": 74, "—": 75, "r": 76, "ø": 77, "ő": 78, "―": 79, "k": 80, "-": 81, "l": 82, "|": 34, "[UNK]": 83, "[PAD]": 84}