adding all files

README.md

@@ -0,0 +1,21 @@
+---
+language:
+- hi
+license: apache-2.0
+tags:
+- generated_from_trainer
+- robust-speech-event
+model-index:
+- name: wav2vec2-large-xls-r-300m-hindi
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# wav2vec2-large-xls-r-300m-hindi
+
+This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7049
+- Wer: 0.3200

added_tokens.json

@@ -0,0 +1 @@
+{"<s>": 72, "</s>": 73}

alphabet.json

@@ -0,0 +1 @@
+{"labels": [" ", "\u0901", "\u0902", "\u0903", "\u0905", "\u0906", "\u0907", "\u0908", "\u0909", "\u090a", "\u090b", "\u090d", "\u090f", "\u0910", "\u0911", "\u0913", "\u0914", "\u0915", "\u0916", "\u0917", "\u0918", "\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", "\u093c", "\u093e", "\u093f", "\u0940", "\u0941", "\u0942", "\u0943", "\u0947", "\u0948", "\u0949", "\u094b", "\u094c", "\u094d", "\u0958", "\u0959", "\u095a", "\u095b", "\u095c", "\u095d", "\u095e", "\u0960", "\u2047", "", "<s>", "</s>"], "is_bpe": false}

config.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": 0.0,
+  "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": 0.0,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0,
+  "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": 0.05,
+  "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": 71,
+  "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": "4.16.0.dev0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 72,
+  "xvector_output_dim": 512
+}

language_model/attrs.json

@@ -0,0 +1 @@
+{"alpha": 0.5, "beta": 1.5, "unk_score_offset": -10.0, "score_boundary": true}

preprocessor_config.json

@@ -0,0 +1,10 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "Wav2Vec2ProcessorWithLM",
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f11f34c09332f167640e2a1f0079a409af1f5efa56c51c5764cfd58d92bb458
+size 1262218865

special_tokens_map.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}]}

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": "|", "special_tokens_map_file": "/workspace/.cache/huggingface/transformers/3bf9b151a0a5aa5bbcf03b4dfc3665c74f8bc0f9b7b4d0dfc9b9327b2d7d75e1.a21d51735cf8667bcd610f057e88548d5d6a381401f6b4501a8bc6c1a9dc8498", "tokenizer_file": null, "name_or_path": "ravirajoshi/wav2vec2-large-xls-r-300m-hindi", "tokenizer_class": "Wav2Vec2CTCTokenizer", "processor_class": "Wav2Vec2ProcessorWithLM"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cdd2bfbe884d6e195ee5731914cde2c0832da08865bef4d1a9ce5921ca68ee6
+size 3055

vocab.json

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