upload model

config.json

@@ -0,0 +1,99 @@
+{
+  "_name_or_path": "microsoft/wavlm-large",
+  "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": false,
+  "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_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_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_min_space": 1,
+  "mask_time_other": 0.0,
+  "mask_time_prob": 0.05,
+  "mask_time_selection": "static",
+  "max_bucket_distance": 800,
+  "model_type": "wav2vec2",
+  "num_adapter_layers": 3,
+  "num_attention_heads": 16,
+  "num_buckets": 320,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_ctc_classes": 80,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 24,
+  "num_negatives": 100,
+  "output_hidden_size": 1024,
+  "pad_token_id": 38,
+  "proj_codevector_dim": 768,
+  "replace_prob": 0.5,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.11.3",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 39
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91efd24a2005c4045520d38f151d2f08794bbf78537813f6eb37829195c38d7d
+size 2490378705

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
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1986049afcd821c8cb272686718253215d26316df10ce87fb33d1315050ac15
+size 1262066879

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de7c509bd86577b8913d86be912c77a1095254b105dd4f670cdd2b78b3018d35
+size 14503

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:947b6a8270538e237b7ce8f531749b4e87461b5205448c391e115b5f0c596643
+size 559

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:941c0c422382fb4856d4f9560e18421fb4ea5d3c208554cecaed7b7c8275bae4
+size 623

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": "|", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

trainer_state.json

@@ -0,0 +1,94 @@
+{
+  "best_metric": 0.5534710884094238,
+  "best_model_checkpoint": "wavlm-tamil-ipa/checkpoint-1000",
+  "epoch": 0.7136485280999108,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.07,
+      "learning_rate": 2.97e-05,
+      "loss": 6.4757,
+      "step": 100
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 5.94e-05,
+      "loss": 2.7305,
+      "step": 200
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 8.939999999999999e-05,
+      "loss": 2.5809,
+      "step": 300
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0001191,
+      "loss": 2.53,
+      "step": 400
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00014879999999999998,
+      "loss": 2.0147,
+      "step": 500
+    },
+    {
+      "epoch": 0.36,
+      "eval_cer": 0.6800635831193839,
+      "eval_loss": 1.4391984939575195,
+      "eval_runtime": 1401.2346,
+      "eval_samples_per_second": 8.599,
+      "eval_steps_per_second": 1.075,
+      "step": 500
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00017849999999999997,
+      "loss": 0.934,
+      "step": 600
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00020819999999999996,
+      "loss": 0.597,
+      "step": 700
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0002382,
+      "loss": 0.4904,
+      "step": 800
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0002676,
+      "loss": 0.4568,
+      "step": 900
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00029759999999999997,
+      "loss": 0.3961,
+      "step": 1000
+    },
+    {
+      "epoch": 0.71,
+      "eval_cer": 0.3502788029525032,
+      "eval_loss": 0.5534710884094238,
+      "eval_runtime": 1403.4751,
+      "eval_samples_per_second": 8.585,
+      "eval_steps_per_second": 1.074,
+      "step": 1000
+    }
+  ],
+  "max_steps": 70050,
+  "num_train_epochs": 50,
+  "total_flos": 6.366682745104583e+18,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:935d121a78eab9fc9e6e8032f0ee448b5799e8cfec09aaceb398163a8ac4331b
+size 2863

vocab.json

@@ -0,0 +1 @@
+{"ʂ": 1, "ɲ": 2, "r": 3, "u": 4, "a": 5, "ʈ": 6, "t͡ʃ": 7, "oː": 8, "m": 9, "p": 10, "aj": 11, "ʋ": 12, "uː": 13, "ɾ": 14, "ŋ": 15, "ɳ": 16, "ɻ": 17, "kʂ": 18, "t̪": 19, "l": 20, "e": 21, "aʋ": 22, "eː": 23, "h": 24, "aː": 25, "k": 26, "ɭ": 27, "்": 28, "i": 29, "n": 30, "o": 31, "iː": 32, "d͡ʒ": 33, "j": 34, "s": 35, "n̪": 36, "|": 0, "[UNK]": 37, "[PAD]": 38}