Delete transcription

transcription/w2v-bert-darija-finetuned-clean/added_tokens.json

@@ -1,4 +0,0 @@
-{
-  "</s>": 57,
-  "<s>": 56
-}

transcription/w2v-bert-darija-finetuned-clean/config.json

@@ -1,82 +0,0 @@
-{
-  "_name_or_path": "facebook/w2v-bert-2.0",
-  "activation_dropout": 0.0,
-  "adapter_act": "relu",
-  "adapter_kernel_size": 3,
-  "adapter_stride": 2,
-  "add_adapter": true,
-  "apply_spec_augment": false,
-  "architectures": [
-    "Wav2Vec2BertForCTC"
-  ],
-  "attention_dropout": 0.0,
-  "bos_token_id": 1,
-  "classifier_proj_size": 768,
-  "codevector_dim": 768,
-  "conformer_conv_dropout": 0.1,
-  "contrastive_logits_temperature": 0.1,
-  "conv_depthwise_kernel_size": 31,
-  "ctc_loss_reduction": "mean",
-  "ctc_zero_infinity": false,
-  "diversity_loss_weight": 0.1,
-  "eos_token_id": 2,
-  "feat_proj_dropout": 0.0,
-  "feat_quantizer_dropout": 0.0,
-  "feature_projection_input_dim": 160,
-  "final_dropout": 0.1,
-  "hidden_act": "swish",
-  "hidden_dropout": 0.0,
-  "hidden_size": 1024,
-  "initializer_range": 0.02,
-  "intermediate_size": 4096,
-  "layer_norm_eps": 1e-05,
-  "layerdrop": 0.0,
-  "left_max_position_embeddings": 64,
-  "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": 0.0,
-  "max_source_positions": 5000,
-  "model_type": "wav2vec2-bert",
-  "num_adapter_layers": 1,
-  "num_attention_heads": 16,
-  "num_codevector_groups": 2,
-  "num_codevectors_per_group": 320,
-  "num_hidden_layers": 24,
-  "num_negatives": 100,
-  "output_hidden_size": 1024,
-  "pad_token_id": 55,
-  "position_embeddings_type": "relative_key",
-  "proj_codevector_dim": 768,
-  "right_max_position_embeddings": 8,
-  "rotary_embedding_base": 10000,
-  "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": "4.46.3",
-  "use_intermediate_ffn_before_adapter": false,
-  "use_weighted_layer_sum": false,
-  "vocab_size": 58,
-  "xvector_output_dim": 512
-}

transcription/w2v-bert-darija-finetuned-clean/preprocessor_config.json

@@ -1,11 +0,0 @@
-{
-  "feature_extractor_type": "SeamlessM4TFeatureExtractor",
-  "feature_size": 80,
-  "num_mel_bins": 80,
-  "padding_side": "right",
-  "padding_value": 0.0,
-  "processor_class": "Wav2Vec2BertProcessor",
-  "return_attention_mask": true,
-  "sampling_rate": 16000,
-  "stride": 2
-}

transcription/w2v-bert-darija-finetuned-clean/special_tokens_map.json

@@ -1,6 +0,0 @@
-{
-  "bos_token": "<s>",
-  "eos_token": "</s>",
-  "pad_token": "[PAD]",
-  "unk_token": "[UNK]"
-}

transcription/w2v-bert-darija-finetuned-clean/tokenizer_config.json

@@ -1,48 +0,0 @@
-{
-  "added_tokens_decoder": {
-    "54": {
-      "content": "[UNK]",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": false
-    },
-    "55": {
-      "content": "[PAD]",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": false
-    },
-    "56": {
-      "content": "<s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "57": {
-      "content": "</s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    }
-  },
-  "bos_token": "<s>",
-  "clean_up_tokenization_spaces": false,
-  "do_lower_case": false,
-  "eos_token": "</s>",
-  "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "[PAD]",
-  "processor_class": "Wav2Vec2BertProcessor",
-  "replace_word_delimiter_char": " ",
-  "target_lang": null,
-  "tokenizer_class": "Wav2Vec2CTCTokenizer",
-  "unk_token": "[UNK]",
-  "word_delimiter_token": "|"
-}

transcription/w2v-bert-darija-finetuned-clean/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b2793aaf5af1a42cb015bfef656c097f2acac87a48fffa9d3175eaeceb802e54
-size 5304

transcription/w2v-bert-darija-finetuned-clean/vocab.json

@@ -1,58 +0,0 @@
-{
-  "\t": 0,
-  "\n": 1,
-  "!": 3,
-  "(": 4,
-  ")": 5,
-  ",": 6,
-  ".": 7,
-  "?": 8,
-  "[PAD]": 55,
-  "[UNK]": 54,
-  "|": 2,
-  "،": 9,
-  "؟": 10,
-  "ء": 11,
-  "آ": 12,
-  "أ": 13,
-  "ؤ": 14,
-  "إ": 15,
-  "ئ": 16,
-  "ا": 17,
-  "ب": 18,
-  "ة": 19,
-  "ت": 20,
-  "ث": 21,
-  "ج": 22,
-  "ح": 23,
-  "خ": 24,
-  "د": 25,
-  "ذ": 26,
-  "ر": 27,
-  "ز": 28,
-  "س": 29,
-  "ش": 30,
-  "ص": 31,
-  "ض": 32,
-  "ط": 33,
-  "ظ": 34,
-  "ع": 35,
-  "غ": 36,
-  "ف": 37,
-  "ق": 38,
-  "ك": 39,
-  "ل": 40,
-  "م": 41,
-  "ن": 42,
-  "ه": 43,
-  "و": 44,
-  "ى": 45,
-  "ي": 46,
-  "ً": 47,
-  "ٍ": 48,
-  "ّ": 49,
-  "ٱ": 50,
-  "پ": 51,
-  "ڤ": 52,
-  "ڭ": 53
-}