Upload 9 files

preprocessor_config.json

@@ -4,7 +4,7 @@
   "feature_size": 1,
   "padding_side": "right",
   "padding_value": 0.0,
-  "processor_class": "Wav2Vec2Processor",
+  "processor_class": "Wav2Vec2ProcessorWithLM",
   "return_attention_mask": true,
   "sampling_rate": 16000
 }

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b630325bd2cc4136cae190fc3e4de0dd6726cf46c99060d577a10df4ad4db35
+size 14308

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5607538ed31c76b932f88c667bde8c976f9888b0675caf3c36b869402b07647
+size 1064

special_tokens_map.json

@@ -0,0 +1,4 @@
+{
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,32 @@
+{
+  "added_tokens_decoder": {
+    "50": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "51": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": null,
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": false,
+  "eos_token": null,
+  "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": "|"
+}

trainer_state.json

@@ -0,0 +1,67 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.970760233918129,
+  "eval_steps": 250,
+  "global_step": 850,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.46,
+      "learning_rate": 1.5e-05,
+      "loss": 0.8043,
+      "step": 250
+    },
+    {
+      "epoch": 1.46,
+      "eval_cer": 0.19486492447697548,
+      "eval_loss": 0.5256313681602478,
+      "eval_runtime": 226.5238,
+      "eval_samples_per_second": 14.586,
+      "eval_steps_per_second": 1.823,
+      "eval_wer": 0.4023366474525127,
+      "step": 250
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 3e-05,
+      "loss": 0.5435,
+      "step": 500
+    },
+    {
+      "epoch": 2.92,
+      "eval_cer": 0.1960657773275714,
+      "eval_loss": 0.4380650520324707,
+      "eval_runtime": 227.8338,
+      "eval_samples_per_second": 14.502,
+      "eval_steps_per_second": 1.813,
+      "eval_wer": 0.3965337150373322,
+      "step": 500
+    },
+    {
+      "epoch": 4.39,
+      "learning_rate": 8.873239436619718e-06,
+      "loss": 0.4827,
+      "step": 750
+    },
+    {
+      "epoch": 4.39,
+      "eval_cer": 0.193239280141815,
+      "eval_loss": 0.4322899878025055,
+      "eval_runtime": 230.4509,
+      "eval_samples_per_second": 14.337,
+      "eval_steps_per_second": 1.792,
+      "eval_wer": 0.398777515571202,
+      "step": 750
+    }
+  ],
+  "logging_steps": 250,
+  "max_steps": 855,
+  "num_train_epochs": 5,
+  "save_steps": 850,
+  "total_flos": 2.8872999396360806e+18,
+  "trial_name": null,
+  "trial_params": null
+}

vocab.json

@@ -0,0 +1,54 @@
+{
+  "[PAD]": 51,
+  "[UNK]": 50,
+  "|": 44,
+  "ء": 3,
+  "آ": 5,
+  "أ": 32,
+  "ؤ": 35,
+  "ئ": 38,
+  "ا": 46,
+  "ب": 25,
+  "ت": 19,
+  "ث": 2,
+  "ج": 49,
+  "ح": 39,
+  "خ": 31,
+  "د": 27,
+  "ذ": 10,
+  "ر": 0,
+  "ز": 33,
+  "س": 28,
+  "ش": 42,
+  "ص": 43,
+  "ض": 26,
+  "ط": 45,
+  "ظ": 15,
+  "ع": 4,
+  "غ": 11,
+  "ف": 8,
+  "ق": 7,
+  "ل": 41,
+  "م": 37,
+  "ن": 36,
+  "ه": 21,
+  "و": 48,
+  "ى": 17,
+  "ي": 22,
+  "ٹ": 9,
+  "پ": 30,
+  "چ": 40,
+  "ڈ": 16,
+  "ڑ": 14,
+  "ژ": 47,
+  "ک": 1,
+  "گ": 13,
+  "ں": 23,
+  "ھ": 24,
+  "ہ": 34,
+  "ۂ": 29,
+  "ۃ": 20,
+  "ی": 6,
+  "ے": 18,
+  "ۓ": 12
+}