Initial commit

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": 72,
+  "transformers_version": "4.4.0",
+  "vocab_size": 73
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:915f39749bdd822f47e68c0477d435a9fd7760c3d590bf63ba9e86e802c006e8
+size 2490675719

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 sha256:835850a7a029e73a8fa6113cd193085d0e470700c4bb45be4e41f630bc8afe34
+size 1262233111

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90a4b7dd943e4433a60f796edbc9ed88f16bd4c3bd4609e41aaaaf622ba391cb
+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": "|"}

trainer_state.json

@@ -0,0 +1,72 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 48.78048780487805,
+  "global_step": 4000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 12.2,
+      "learning_rate": 0.0004200542005420054,
+      "loss": 2.2288,
+      "step": 1000
+    },
+    {
+      "epoch": 12.2,
+      "eval_loss": 0.4119809865951538,
+      "eval_runtime": 39.8264,
+      "eval_samples_per_second": 7.307,
+      "eval_wer": 0.4587706146926537,
+      "step": 1000
+    },
+    {
+      "epoch": 24.39,
+      "learning_rate": 0.0002845528455284553,
+      "loss": 0.1307,
+      "step": 2000
+    },
+    {
+      "epoch": 24.39,
+      "eval_loss": 0.46079644560813904,
+      "eval_runtime": 39.8036,
+      "eval_samples_per_second": 7.311,
+      "eval_wer": 0.3800599700149925,
+      "step": 2000
+    },
+    {
+      "epoch": 36.59,
+      "learning_rate": 0.00014905149051490515,
+      "loss": 0.0645,
+      "step": 3000
+    },
+    {
+      "epoch": 36.59,
+      "eval_loss": 0.4456443190574646,
+      "eval_runtime": 41.0007,
+      "eval_samples_per_second": 7.097,
+      "eval_wer": 0.35007496251874065,
+      "step": 3000
+    },
+    {
+      "epoch": 48.78,
+      "learning_rate": 1.3550135501355015e-05,
+      "loss": 0.042,
+      "step": 4000
+    },
+    {
+      "epoch": 48.78,
+      "eval_loss": 0.46975016593933105,
+      "eval_runtime": 40.134,
+      "eval_samples_per_second": 7.251,
+      "eval_wer": 0.3365817091454273,
+      "step": 4000
+    }
+  ],
+  "max_steps": 4100,
+  "num_train_epochs": 50,
+  "total_flos": 1.961718571271133e+19,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9eb3b3eafe5ebea11421306fb6d11ffc66297eddda9495cddcfd0a7770a2b8e
+size 2287

vocab.json

@@ -0,0 +1 @@
+{"ិ": 0, "វ": 1, "ះ": 2, "ង": 3, "ឈ": 4, "៊": 5, "ៀ": 6, "ស": 7, "ណ": 8, "ឍ": 9, "ឱ": 10, "ឧ": 11, "ែ": 12, "ឋ": 13, "ឆ": 14, "ៅ": 15, "ដ": 16, "ល": 17, "ត": 18, "ុ": 19, "ៃ": 20, "ឪ": 21, "ឌ": 22, "ព": 23, "ឮ": 24, "ហ": 25, "រ": 26, "ៈ": 27, "័": 28, "៎": 29, "ោ": 30, "ឭ": 31, "៍": 32, "ឡ": 33, "ប": 34, "៌": 36, "យ": 37, "ច": 38, "េ": 39, "ឥ": 40, "ឬ": 41, "ំ": 42, "ើ": 43, "ួ": 44, "ន": 45, "ថ": 46, "ភ": 47, "ឯ": 48, "ញ": 49, "ី": 50, "ផ": 51, "ឺ": 52, "ជ": 53, "់": 54, "ទ": 55, "្": 56, "៏": 57, "ឃ": 58, "ធ": 59, "អ": 60, "៉": 61, "ម": 62, "ឿ": 63, "ូ": 64, "ឹ": 65, "ឫ": 66, "គ": 67, "ក": 68, "ា": 69, "ខ": 70, "|": 35, "[UNK]": 71, "[PAD]": 72}