Adding model hindi XLSR. Params bs 16 and lr 2e-5.

config.json

@@ -0,0 +1,76 @@
+{
+  "_name_or_path": "facebook/wav2vec2-large-xlsr-53",
+  "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": 71,
+  "transformers_version": "4.5.0",
+  "vocab_size": 72
+}

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:df228c26d9431a55569a3f0abc4aa52537a3bcb58507dbcb36e9cd4b3bbfaa7a
+size 1262229015

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 @@
+{"ँ": 0, "ग": 1, "ऊ": 2, "ो": 3, "ग़": 4, "ड": 5, "ट": 6, "ण": 7, "ढ़": 8, "ॉ": 9, "ए": 10, "प": 11, "द": 12, "झ": 13, "़": 14, "ं": 15, "ृ": 16, "घ": 17, "भ": 18, "स": 19, "छ": 20, "ि": 21, "ठ": 22, "क़": 23, "क": 24, "ः": 25, "ह": 26, "औ": 27, "ज": 28, "ा": 29, "ओ": 30, "त": 31, "्": 32, "ऋ": 33, "ऐ": 34, "ध": 35, "ई": 36, "ी": 37, "थ": 38, "ञ": 39, "ज़": 40, "ल": 41, "ू": 42, "ख": 43, "ढ": 44, "च": 45, "ऑ": 46, "ब": 47, "न": 48, "व": 50, "श": 51, "फ": 52, "आ": 53, "य": 54, "ख़": 55, "ौ": 56, "ड़": 57, "र": 58, "इ": 59, "ऍ": 60, "अ": 61, "म": 62, "फ़": 63, "ॠ": 64, "ै": 65, "उ": 66, "ष": 67, "ु": 68, "े": 69, "|": 49, "[UNK]": 70, "[PAD]": 71}