Upload 5 files

alphabet.json

@@ -0,0 +1 @@
+{"labels": ["", "<s>", "</s>", "\u2047", " ", "0", "1", "2", "3", "4", "5", "6", "7", "8", "9", "\u0901", "\u0902", "\u0903", "\u0905", "\u0906", "\u0907", "\u0908", "\u0909", "\u090a", "\u090b", "\u090f", "\u0910", "\u0911", "\u0913", "\u0914", "\u0915", "\u0916", "\u0917", "\u0918", "\u0919", "\u091a", "\u091b", "\u091c", "\u091d", "\u091e", "\u091f", "\u0920", "\u0921", "\u0922", "\u0923", "\u0924", "\u0925", "\u0926", "\u0927", "\u0928", "\u092a", "\u092b", "\u092c", "\u092d", "\u092e", "\u092f", "\u0930", "\u0932", "\u0935", "\u0936", "\u0937", "\u0938", "\u0939", "\u093e", "\u093f", "\u0940", "\u0941", "\u0942", "\u0943", "\u0945", "\u0947", "\u0948", "\u0949", "\u094b", "\u094c", "\u094d", "\u0958", "\u0959", "\u095a", "\u095b", "\u095c", "\u095d", "\u095e", "\u095f"], "is_bpe": false}

config.json

@@ -1,7 +1,6 @@
 {
-  "_name_or_path": "Harveenchadha/hindi_base_wav2vec2",
+  "_name_or_path": "facebook/wav2vec2-base-960h",
   "activation_dropout": 0.1,
-  "adapter_attn_dim": null,
   "adapter_kernel_size": 3,
   "adapter_stride": 2,
   "add_adapter": false,
@@ -9,7 +8,7 @@
   "architectures": [
     "Wav2Vec2ForCTC"
   ],
-  "attention_dropout": 0.0,
+  "attention_dropout": 0.1,
   "bos_token_id": 1,
   "classifier_proj_size": 256,
   "codevector_dim": 256,
@@ -42,7 +41,7 @@
     2,
     2
   ],
-  "ctc_loss_reduction": "mean",
+  "ctc_loss_reduction": "sum",
   "ctc_zero_infinity": false,
   "diversity_loss_weight": 0.1,
   "do_stable_layer_norm": false,
@@ -50,18 +49,18 @@
   "feat_extract_activation": "gelu",
   "feat_extract_dropout": 0.0,
   "feat_extract_norm": "group",
-  "feat_proj_dropout": 0.0,
+  "feat_proj_dropout": 0.1,
   "feat_quantizer_dropout": 0.0,
   "final_dropout": 0.1,
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
-  "hidden_dropout": 0.0,
+  "hidden_dropout": 0.1,
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "layer_norm_eps": 1e-05,
-  "layerdrop": 0.0,
+  "layerdrop": 0.1,
   "mask_feature_length": 10,
   "mask_feature_min_masks": 0,
   "mask_feature_prob": 0.0,
@@ -103,7 +102,7 @@
     1
   ],
   "torch_dtype": "float32",
-  "transformers_version": "4.34.0",
+  "transformers_version": "4.15.0",
   "use_weighted_layer_sum": false,
   "vocab_size": 84,
   "xvector_output_dim": 512

preprocessor_config.json

@@ -3,7 +3,8 @@
   "feature_extractor_type": "Wav2Vec2FeatureExtractor",
   "feature_size": 1,
   "padding_side": "right",
-  "padding_value": 0.0,
-  "return_attention_mask": true,
-  "sampling_rate": 16000
+  "padding_value": 0,
+  "return_attention_mask": false,
+  "sampling_rate": 16000,
+  "processor_class": "Wav2Vec2ProcessorWithLM"
 }

special_tokens_map.json

@@ -1,6 +1 @@
-{
-  "bos_token": "<s>",
-  "eos_token": "</s>",
-  "pad_token": "<pad>",
-  "unk_token": "<unk>"
-}
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}

tokenizer_config.json

@@ -1,49 +1 @@
-{
-  "added_tokens_decoder": {
-    "0": {
-      "content": "<pad>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": false
-    },
-    "1": {
-      "content": "<s>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": false
-    },
-    "2": {
-      "content": "</s>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": false
-    },
-    "3": {
-      "content": "<unk>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": false
-    }
-  },
-  "additional_special_tokens": [],
-  "bos_token": "<s>",
-  "clean_up_tokenization_spaces": true,
-  "do_lower_case": false,
-  "eos_token": "</s>",
-  "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<pad>",
-  "replace_word_delimiter_char": " ",
-  "target_lang": null,
-  "tokenizer_class": "Wav2Vec2CTCTokenizer",
-  "tokenizer_file": null,
-  "unk_token": "<unk>",
-  "word_delimiter_token": "|"
-}
+{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "<pad>", "do_lower_case": false, "word_delimiter_token": "|", "tokenizer_class": "Wav2Vec2CTCTokenizer"}