Upload wav2vec2-XLS-R Telugu ASR final checkpoint (extended-patience, full 50-epoch run)

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 70,
+  "<s>": 69
+}

config.json

@@ -0,0 +1,109 @@
+{
+  "activation_dropout": 0.0,
+  "adapter_attn_dim": null,
+  "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": true,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": true,
+  "dtype": "float32",
+  "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": 0.1,
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.1,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.1,
+  "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": 68,
+  "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
+  ],
+  "transformers_version": "5.12.1",
+  "use_cache": false,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 69,
+  "xvector_output_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:538d09285a082776ea254d795aca3b8dbad6a8f5a15d234fac8a6bdd777aa3ba
+size 1262090332

preprocessor_config.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
+}

processor_config.json

@@ -0,0 +1,12 @@
+{
+  "feature_extractor": {
+    "do_normalize": true,
+    "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+    "feature_size": 1,
+    "padding_side": "right",
+    "padding_value": 0.0,
+    "return_attention_mask": true,
+    "sampling_rate": 16000
+  },
+  "processor_class": "Wav2Vec2Processor"
+}

tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "added_tokens_decoder": {
+    "66": {
+      "content": "|",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "67": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "68": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "69": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "70": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "backend": "custom",
+  "bos_token": "<s>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "processor_class": "Wav2Vec2Processor",
+  "replace_word_delimiter_char": " ",
+  "target_lang": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61cf01e106f51b63233f4bc5f2cfa55d8418aeb9937a17d3373544fb8b12fb98
+size 5201

vocab.json

@@ -0,0 +1,71 @@
+{
+  "[PAD]": 68,
+  "[UNK]": 67,
+  "|": 66,
+  "ఁ": 0,
+  "ం": 1,
+  "ః": 2,
+  "అ": 3,
+  "ఆ": 4,
+  "ఇ": 5,
+  "ఈ": 6,
+  "ఉ": 7,
+  "ఊ": 8,
+  "ఋ": 9,
+  "ఎ": 10,
+  "ఏ": 11,
+  "ఐ": 12,
+  "ఒ": 13,
+  "ఓ": 14,
+  "ఔ": 15,
+  "క": 16,
+  "ఖ": 17,
+  "గ": 18,
+  "ఘ": 19,
+  "ఙ": 20,
+  "చ": 21,
+  "ఛ": 22,
+  "జ": 23,
+  "ఝ": 24,
+  "ఞ": 25,
+  "ట": 26,
+  "ఠ": 27,
+  "డ": 28,
+  "ఢ": 29,
+  "ణ": 30,
+  "త": 31,
+  "థ": 32,
+  "ద": 33,
+  "ధ": 34,
+  "న": 35,
+  "ప": 36,
+  "ఫ": 37,
+  "బ": 38,
+  "భ": 39,
+  "మ": 40,
+  "య": 41,
+  "ర": 42,
+  "ఱ": 43,
+  "ల": 44,
+  "ళ": 45,
+  "వ": 46,
+  "శ": 47,
+  "ష": 48,
+  "స": 49,
+  "హ": 50,
+  "ా": 51,
+  "ి": 52,
+  "ీ": 53,
+  "ు": 54,
+  "ూ": 55,
+  "ృ": 56,
+  "ె": 57,
+  "ే": 58,
+  "ై": 59,
+  "ొ": 60,
+  "ో": 61,
+  "ౌ": 62,
+  "్": 63,
+  "ౖ": 64,
+  "౦": 65
+}