End of training

README.md

@@ -0,0 +1,58 @@
+---
+license: apache-2.0
+base_model: facebook/wav2vec2-xls-r-300m
+tags:
+- generated_from_trainer
+datasets:
+- common_voice_11_0
+model-index:
+- name: wav2vec2-large-xlsr-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-xlsr-hindi
+
+This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the common_voice_11_0 dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0003
+- train_batch_size: 10
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 3
+- total_train_batch_size: 30
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 5
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu118
+- Datasets 2.15.0
+- Tokenizers 0.15.0

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "</s>": 92,
+  "<s>": 91,
+  "[PAD]": 90
+}

config.json

@@ -0,0 +1,108 @@
+{
+  "_name_or_path": "facebook/wav2vec2-xls-r-300m",
+  "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": 0.0,
+  "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,
+  "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": 90,
+  "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": "4.35.2",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 93,
+  "xvector_output_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61d5f4169818738895be87c7ffd634e5c4f68b9bbdf3d773f29d9b75c8713e74
+size 1262188780

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": "Wav2Vec2Processor",
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

runs/Nov29_05-52-16_e87d2f3439a3/events.out.tfevents.1701238216.e87d2f3439a3.2698.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec13cb156bbc37deefa3f38af09e323363228ffdf841ffd7f50fa5f3bf3de5c0
+size 6076

runs/Nov29_06-17-01_e87d2f3439a3/events.out.tfevents.1701238650.e87d2f3439a3.2698.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86ad381a7a338342b17c72fc5acbfebdd1ff3f53f195a3ba594fdada6f444ae4
+size 6071

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,48 @@
+{
+  "added_tokens_decoder": {
+    "89": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "90": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "91": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "92": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "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 sha256:9fd1368709ecb12dac55ee3b886299d6073b8c84a729943afc610940762aad61
+size 4600

vocab.json

@@ -0,0 +1,93 @@
+{
+  "[PAD]": 90,
+  "[UNK]": 89,
+  "a": 1,
+  "b": 2,
+  "c": 3,
+  "d": 4,
+  "e": 5,
+  "f": 6,
+  "g": 7,
+  "h": 8,
+  "i": 9,
+  "k": 10,
+  "l": 11,
+  "m": 12,
+  "n": 13,
+  "o": 14,
+  "p": 15,
+  "q": 16,
+  "r": 17,
+  "s": 18,
+  "t": 19,
+  "u": 20,
+  "v": 21,
+  "w": 22,
+  "x": 23,
+  "z": 24,
+  "|": 0,
+  "ँ": 26,
+  "ं": 27,
+  "ः": 28,
+  "अ": 29,
+  "आ": 30,
+  "इ": 31,
+  "ई": 32,
+  "उ": 33,
+  "ऊ": 34,
+  "ए": 35,
+  "ऐ": 36,
+  "ऑ": 37,
+  "ओ": 38,
+  "औ": 39,
+  "क": 40,
+  "ख": 41,
+  "ग": 42,
+  "घ": 43,
+  "च": 44,
+  "छ": 45,
+  "ज": 46,
+  "झ": 47,
+  "ञ": 48,
+  "ट": 49,
+  "ठ": 50,
+  "ड": 51,
+  "ढ": 52,
+  "ण": 53,
+  "त": 54,
+  "थ": 55,
+  "द": 56,
+  "ध": 57,
+  "न": 58,
+  "प": 59,
+  "फ": 60,
+  "ब": 61,
+  "भ": 62,
+  "म": 63,
+  "य": 64,
+  "र": 65,
+  "ल": 66,
+  "व": 67,
+  "श": 68,
+  "ष": 69,
+  "स": 70,
+  "ह": 71,
+  "़": 72,
+  "ा": 73,
+  "ि": 74,
+  "ी": 75,
+  "ु": 76,
+  "ू": 77,
+  "ृ": 78,
+  "े": 79,
+  "ै": 80,
+  "ॉ": 81,
+  "ो": 82,
+  "ौ": 83,
+  "्": 84,
+  "ड़": 85,
+  "ढ़": 86,
+  "फ़": 87,
+  "।": 88,
+  "’": 89
+}