add tokenizer

.ipynb_checkpoints/added_tokens-checkpoint.json

@@ -0,0 +1 @@
+{"<s>": 42, "</s>": 43}

.ipynb_checkpoints/config-checkpoint.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": 0.0,
+  "mask_feature_length": 64,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.25,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.75,
+  "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": 41,
+  "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": "4.17.0.dev0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 44,
+  "xvector_output_dim": 512
+}

.ipynb_checkpoints/preprocessor_config-checkpoint.json

@@ -0,0 +1,9 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

.ipynb_checkpoints/special_tokens_map-checkpoint.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}]}

.ipynb_checkpoints/tokenizer_config-checkpoint.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": "/workspace/container_0/model/", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

.ipynb_checkpoints/vocab-checkpoint.json

@@ -0,0 +1 @@
+{"aa": 1, "ae": 2, "ah": 3, "aw": 4, "ay": 5, "b": 6, "ch": 7, "d": 8, "dh": 9, "dx": 10, "eh": 11, "er": 12, "ey": 13, "f": 14, "g": 15, "h#": 16, "hh": 17, "ih": 18, "iy": 19, "jh": 20, "k": 21, "l": 22, "m": 23, "n": 24, "ng": 25, "ow": 26, "oy": 27, "p": 28, "r": 29, "s": 30, "sh": 31, "t": 32, "th": 33, "uh": 34, "uw": 35, "v": 36, "w": 37, "y": 38, "z": 39, "|": 0, "[UNK]": 40, "[PAD]": 41}