add files

.gitignore

@@ -0,0 +1,2 @@
+checkpoint-* 
+*.txt

README.md

@@ -0,0 +1 @@
+Model page for FYTM_cv_all

all_results.json

@@ -0,0 +1,23 @@
+{
+    "epoch": 40.0,
+    "eval_loss": 0.38463133573532104,
+    "eval_mem_cpu_alloc_delta": 36864,
+    "eval_mem_cpu_peaked_delta": 0,
+    "eval_mem_gpu_alloc_delta": 0,
+    "eval_mem_gpu_peaked_delta": 807446528,
+    "eval_runtime": 34.3132,
+    "eval_samples": 405,
+    "eval_samples_per_second": 11.803,
+    "eval_wer": 0.3688760806916426,
+    "init_mem_cpu_alloc_delta": 0,
+    "init_mem_cpu_peaked_delta": 0,
+    "init_mem_gpu_alloc_delta": 0,
+    "init_mem_gpu_peaked_delta": 0,
+    "train_mem_cpu_alloc_delta": 429268992,
+    "train_mem_cpu_peaked_delta": 10952704,
+    "train_mem_gpu_alloc_delta": 3826897920,
+    "train_mem_gpu_peaked_delta": 1210447360,
+    "train_runtime": 7468.243,
+    "train_samples": 1618,
+    "train_samples_per_second": 1.082
+}

config.json

@@ -0,0 +1,76 @@
+{
+  "_name_or_path": "/wav2vec2-large-xlsr-indonesian",
+  "activation_dropout": 0.1,
+  "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": true,
+  "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": 28,
+  "transformers_version": "4.6.0",
+  "vocab_size": 29
+}

eval_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 40.0,
+    "eval_loss": 0.38463133573532104,
+    "eval_mem_cpu_alloc_delta": 36864,
+    "eval_mem_cpu_peaked_delta": 0,
+    "eval_mem_gpu_alloc_delta": 0,
+    "eval_mem_gpu_peaked_delta": 807446528,
+    "eval_runtime": 34.3132,
+    "eval_samples": 405,
+    "eval_samples_per_second": 11.803,
+    "eval_wer": 0.3688760806916426
+}

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:cdc09460276b6fd1915194cfb7ac6ac58a47e380fff6ede7e842d45037e7e08d
+size 1262042545

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": " "}

train_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 40.0,
+    "init_mem_cpu_alloc_delta": 0,
+    "init_mem_cpu_peaked_delta": 0,
+    "init_mem_gpu_alloc_delta": 0,
+    "init_mem_gpu_peaked_delta": 0,
+    "train_mem_cpu_alloc_delta": 429268992,
+    "train_mem_cpu_peaked_delta": 10952704,
+    "train_mem_gpu_alloc_delta": 3826897920,
+    "train_mem_gpu_peaked_delta": 1210447360,
+    "train_runtime": 7468.243,
+    "train_samples": 1618,
+    "train_samples_per_second": 1.082
+}

trainer_state.json

@@ -0,0 +1,247 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 39.99753086419753,
+  "global_step": 8080,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.47,
+      "learning_rate": 4.96e-05,
+      "loss": 6.1701,
+      "step": 500
+    },
+    {
+      "epoch": 2.47,
+      "eval_loss": 2.8719067573547363,
+      "eval_runtime": 34.3427,
+      "eval_samples_per_second": 11.793,
+      "eval_wer": 1.0,
+      "step": 500
+    },
+    {
+      "epoch": 4.95,
+      "learning_rate": 9.960000000000001e-05,
+      "loss": 1.9379,
+      "step": 1000
+    },
+    {
+      "epoch": 4.95,
+      "eval_loss": 0.8804072737693787,
+      "eval_runtime": 34.3595,
+      "eval_samples_per_second": 11.787,
+      "eval_wer": 0.6778097982708934,
+      "step": 1000
+    },
+    {
+      "epoch": 7.42,
+      "learning_rate": 9.299435028248588e-05,
+      "loss": 1.0455,
+      "step": 1500
+    },
+    {
+      "epoch": 7.42,
+      "eval_loss": 0.6408620476722717,
+      "eval_runtime": 34.2855,
+      "eval_samples_per_second": 11.813,
+      "eval_wer": 0.5227665706051873,
+      "step": 1500
+    },
+    {
+      "epoch": 9.9,
+      "learning_rate": 8.593220338983051e-05,
+      "loss": 0.7456,
+      "step": 2000
+    },
+    {
+      "epoch": 9.9,
+      "eval_loss": 0.6179625391960144,
+      "eval_runtime": 34.3686,
+      "eval_samples_per_second": 11.784,
+      "eval_wer": 0.4755043227665706,
+      "step": 2000
+    },
+    {
+      "epoch": 12.38,
+      "learning_rate": 7.887005649717515e-05,
+      "loss": 0.5543,
+      "step": 2500
+    },
+    {
+      "epoch": 12.38,
+      "eval_loss": 0.4895203411579132,
+      "eval_runtime": 34.1759,
+      "eval_samples_per_second": 11.85,
+      "eval_wer": 0.4340057636887608,
+      "step": 2500
+    },
+    {
+      "epoch": 14.85,
+      "learning_rate": 7.180790960451977e-05,
+      "loss": 0.4526,
+      "step": 3000
+    },
+    {
+      "epoch": 14.85,
+      "eval_loss": 0.4277503192424774,
+      "eval_runtime": 34.18,
+      "eval_samples_per_second": 11.849,
+      "eval_wer": 0.42536023054755046,
+      "step": 3000
+    },
+    {
+      "epoch": 17.33,
+      "learning_rate": 6.474576271186441e-05,
+      "loss": 0.3827,
+      "step": 3500
+    },
+    {
+      "epoch": 17.33,
+      "eval_loss": 0.3866088092327118,
+      "eval_runtime": 34.3584,
+      "eval_samples_per_second": 11.788,
+      "eval_wer": 0.414985590778098,
+      "step": 3500
+    },
+    {
+      "epoch": 19.8,
+      "learning_rate": 5.7683615819209045e-05,
+      "loss": 0.3226,
+      "step": 4000
+    },
+    {
+      "epoch": 19.8,
+      "eval_loss": 0.38195741176605225,
+      "eval_runtime": 34.2414,
+      "eval_samples_per_second": 11.828,
+      "eval_wer": 0.392507204610951,
+      "step": 4000
+    },
+    {
+      "epoch": 22.28,
+      "learning_rate": 5.0635593220338987e-05,
+      "loss": 0.295,
+      "step": 4500
+    },
+    {
+      "epoch": 22.28,
+      "eval_loss": 0.41771677136421204,
+      "eval_runtime": 34.2045,
+      "eval_samples_per_second": 11.841,
+      "eval_wer": 0.3919308357348703,
+      "step": 4500
+    },
+    {
+      "epoch": 24.75,
+      "learning_rate": 4.357344632768362e-05,
+      "loss": 0.2613,
+      "step": 5000
+    },
+    {
+      "epoch": 24.75,
+      "eval_loss": 0.41437995433807373,
+      "eval_runtime": 34.2585,
+      "eval_samples_per_second": 11.822,
+      "eval_wer": 0.3855907780979827,
+      "step": 5000
+    },
+    {
+      "epoch": 27.23,
+      "learning_rate": 3.651129943502825e-05,
+      "loss": 0.228,
+      "step": 5500
+    },
+    {
+      "epoch": 27.23,
+      "eval_loss": 0.4071010947227478,
+      "eval_runtime": 34.2741,
+      "eval_samples_per_second": 11.817,
+      "eval_wer": 0.38962536023054756,
+      "step": 5500
+    },
+    {
+      "epoch": 29.7,
+      "learning_rate": 2.9449152542372883e-05,
+      "loss": 0.2081,
+      "step": 6000
+    },
+    {
+      "epoch": 29.7,
+      "eval_loss": 0.3746974468231201,
+      "eval_runtime": 34.1866,
+      "eval_samples_per_second": 11.847,
+      "eval_wer": 0.38213256484149855,
+      "step": 6000
+    },
+    {
+      "epoch": 32.18,
+      "learning_rate": 2.2387005649717515e-05,
+      "loss": 0.1906,
+      "step": 6500
+    },
+    {
+      "epoch": 32.18,
+      "eval_loss": 0.396076500415802,
+      "eval_runtime": 34.2512,
+      "eval_samples_per_second": 11.824,
+      "eval_wer": 0.37175792507204614,
+      "step": 6500
+    },
+    {
+      "epoch": 34.65,
+      "learning_rate": 1.535310734463277e-05,
+      "loss": 0.1752,
+      "step": 7000
+    },
+    {
+      "epoch": 34.65,
+      "eval_loss": 0.37449249625205994,
+      "eval_runtime": 34.2395,
+      "eval_samples_per_second": 11.828,
+      "eval_wer": 0.3729106628242075,
+      "step": 7000
+    },
+    {
+      "epoch": 37.13,
+      "learning_rate": 8.290960451977402e-06,
+      "loss": 0.176,
+      "step": 7500
+    },
+    {
+      "epoch": 37.13,
+      "eval_loss": 0.3883863687515259,
+      "eval_runtime": 34.2865,
+      "eval_samples_per_second": 11.812,
+      "eval_wer": 0.37118155619596543,
+      "step": 7500
+    },
+    {
+      "epoch": 39.6,
+      "learning_rate": 1.228813559322034e-06,
+      "loss": 0.1531,
+      "step": 8000
+    },
+    {
+      "epoch": 39.6,
+      "eval_loss": 0.3848457336425781,
+      "eval_runtime": 34.1853,
+      "eval_samples_per_second": 11.847,
+      "eval_wer": 0.368299711815562,
+      "step": 8000
+    },
+    {
+      "epoch": 40.0,
+      "step": 8080,
+      "total_flos": 3.820109864655936e+16,
+      "train_runtime": 7468.243,
+      "train_samples_per_second": 1.082
+    }
+  ],
+  "max_steps": 8080,
+  "num_train_epochs": 40,
+  "total_flos": 3.820109864655936e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a5f6240899039c0c218f434b65298bd074553c3b87d7b78557f45211b4bae09
+size 2479

vocab.json

@@ -0,0 +1 @@
+{"c": 0, " ": 1, "q": 2, "v": 3, "m": 4, "e": 5, "j": 6, "y": 7, "u": 8, "h": 9, "a": 10, "k": 11, "b": 12, "d": 13, "r": 14, "p": 15, "t": 16, "n": 17, "s": 18, "w": 19, "g": 20, "z": 21, "f": 22, "o": 23, "i": 24, "l": 25, "x": 26, "[UNK]": 27, "[PAD]": 28}