Upload 8 files

config.json

@@ -0,0 +1,76 @@
+{
+  "_name_or_path": "facebook/wav2vec2-large-xlsr-53",
+  "activation_dropout": 0.0,
+  "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": 51,
+  "transformers_version": "4.5.0.dev0",
+  "vocab_size": 52
+}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b9f00cc9527b5d78c29485352d1ba904a45079957533b56dcf7620cf4ab2cc7
+size 1261983472

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 sha256:06846fb6fa11965e4dffb916e4d0f36c48c2ca12eb9b8387dadb4829ba49cf66
+size 1262147031

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": "|"}

trainer_state.json

@@ -0,0 +1,100 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 20.337552742616033,
+  "global_step": 2400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 3.39,
+      "learning_rate": 0.00023999999999999998,
+      "loss": 6.3317,
+      "step": 400
+    },
+    {
+      "epoch": 3.39,
+      "eval_loss": 3.161163806915283,
+      "eval_runtime": 205.0119,
+      "eval_samples_per_second": 8.687,
+      "eval_wer": 1.0,
+      "step": 400
+    },
+    {
+      "epoch": 6.78,
+      "learning_rate": 0.0002703947368421052,
+      "loss": 1.6739,
+      "step": 800
+    },
+    {
+      "epoch": 6.78,
+      "eval_loss": 0.6274727582931519,
+      "eval_runtime": 205.8605,
+      "eval_samples_per_second": 8.651,
+      "eval_wer": 1.008992553042012,
+      "step": 800
+    },
+    {
+      "epoch": 10.17,
+      "learning_rate": 0.00023092105263157893,
+      "loss": 0.3726,
+      "step": 1200
+    },
+    {
+      "epoch": 10.17,
+      "eval_loss": 0.6007506847381592,
+      "eval_runtime": 208.514,
+      "eval_samples_per_second": 8.541,
+      "eval_wer": 0.9197695658282984,
+      "step": 1200
+    },
+    {
+      "epoch": 13.56,
+      "learning_rate": 0.00019144736842105262,
+      "loss": 0.2323,
+      "step": 1600
+    },
+    {
+      "epoch": 13.56,
+      "eval_loss": 0.62809157371521,
+      "eval_runtime": 207.5386,
+      "eval_samples_per_second": 8.582,
+      "eval_wer": 0.9513840101166222,
+      "step": 1600
+    },
+    {
+      "epoch": 16.95,
+      "learning_rate": 0.00015197368421052628,
+      "loss": 0.1598,
+      "step": 2000
+    },
+    {
+      "epoch": 16.95,
+      "eval_loss": 0.679410994052887,
+      "eval_runtime": 213.3742,
+      "eval_samples_per_second": 8.347,
+      "eval_wer": 0.8642686525221301,
+      "step": 2000
+    },
+    {
+      "epoch": 20.34,
+      "learning_rate": 0.0001125,
+      "loss": 0.1258,
+      "step": 2400
+    },
+    {
+      "epoch": 20.34,
+      "eval_loss": 0.7365503311157227,
+      "eval_runtime": 210.0426,
+      "eval_samples_per_second": 8.479,
+      "eval_wer": 0.8294225094843333,
+      "step": 2400
+    }
+  ],
+  "max_steps": 3540,
+  "num_train_epochs": 30,
+  "total_flos": 1.022364819420586e+19,
+  "trial_name": null,
+  "trial_params": null
+}

vocab.json

@@ -0,0 +1 @@
+{"ந": 0, "ா": 1, "ஈ": 2, "ி": 3, "க": 4, "ப": 5, "ஷ": 6, "ஓ": 7, "ட": 8, "ஏ": 9, "ஜ": 10, "ொ": 11, "ஹ": 12, "ம": 14, "’": 15, "ய": 16, "ீ": 17, "ஊ": 18, "ஔ": 19, "ஸ": 20, "ே": 21, "ங": 22, "எ": 23, "்": 24, "ல": 25, "த": 26, "ற": 27, "ூ": 28, "ச": 29, "ு": 30, "'": 31, "அ": 32, "ஒ": 33, "இ": 34, "வ": 35, "ை": 36, "ோ": 37, "ஆ": 38, "ஃ": 39, "ன": 40, "ண": 41, "ஞ": 42, "ர": 43, "உ": 44, "ௌ": 45, "ெ": 46, "ஐ": 47, "ள": 48, "ழ": 49, "|": 13, "[UNK]": 50, "[PAD]": 51}