add new model with high performance

v3.0/all_results.json

@@ -0,0 +1,23 @@
+{
+    "epoch": 25.0,
+    "eval_loss": 0.4074177145957947,
+    "eval_mem_cpu_alloc_delta": 196608,
+    "eval_mem_cpu_peaked_delta": 0,
+    "eval_mem_gpu_alloc_delta": 0,
+    "eval_mem_gpu_peaked_delta": 6052522496,
+    "eval_runtime": 8.723,
+    "eval_samples": 100,
+    "eval_samples_per_second": 11.464,
+    "eval_wer": 0.3398294762484775,
+    "init_mem_cpu_alloc_delta": 1825918976,
+    "init_mem_cpu_peaked_delta": 805171200,
+    "init_mem_gpu_alloc_delta": 1261947904,
+    "init_mem_gpu_peaked_delta": 0,
+    "train_mem_cpu_alloc_delta": 24597475328,
+    "train_mem_cpu_peaked_delta": 1317408768,
+    "train_mem_gpu_alloc_delta": 5099735040,
+    "train_mem_gpu_peaked_delta": 17958715904,
+    "train_runtime": 258038.6163,
+    "train_samples": 196741,
+    "train_samples_per_second": 0.596
+}

v3.0/config.json

@@ -0,0 +1,80 @@
+{
+  "_name_or_path": "/workspace/output_models/wav2vec2-large-xlsr-53/checkpoint-86800",
+  "activation_dropout": 0.055,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.094,
+  "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": 0.04,
+  "final_dropout": 0.0,
+  "gradient_checkpointing": true,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.047,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.041,
+  "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": 0.2,
+  "mask_time_selection": "static",
+  "model_type": "wav2vec2",
+  "normalize_type": "batch",
+  "normalize_wav2vec": true,
+  "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": 1,
+  "pooling_type": "max",
+  "time_pooling_size": 1,
+  "transformers_version": "4.5.0.dev0",
+  "vocab_size": 47
+}

v3.0/eval_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 25.0,
+    "eval_loss": 0.4074177145957947,
+    "eval_mem_cpu_alloc_delta": 196608,
+    "eval_mem_cpu_peaked_delta": 0,
+    "eval_mem_gpu_alloc_delta": 0,
+    "eval_mem_gpu_peaked_delta": 6052522496,
+    "eval_runtime": 8.723,
+    "eval_samples": 100,
+    "eval_samples_per_second": 11.464,
+    "eval_wer": 0.3398294762484775
+}

v3.0/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
+}

v3.0/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5effc7347c30aa34a7e713f62d14299c5873b9a1d4273a0cabc1380a2b041a8b
+size 1262126615

v3.0/results.txt

@@ -0,0 +1,2 @@
+WER=12.819839226606419
+CER=4.402633557742363

v3.0/special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<bos>", "eos_token": "<eos>", "unk_token": "<unk>", "pad_token": "<pad>"}

v3.0/tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "<unk>", "bos_token": "<bos>", "eos_token": "<eos>", "pad_token": "<pad>", "do_lower_case": false, "word_delimiter_token": "|"}

v3.0/train_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 25.0,
+    "init_mem_cpu_alloc_delta": 1825918976,
+    "init_mem_cpu_peaked_delta": 805171200,
+    "init_mem_gpu_alloc_delta": 1261947904,
+    "init_mem_gpu_peaked_delta": 0,
+    "train_mem_cpu_alloc_delta": 24597475328,
+    "train_mem_cpu_peaked_delta": 1317408768,
+    "train_mem_gpu_alloc_delta": 5099735040,
+    "train_mem_gpu_peaked_delta": 17958715904,
+    "train_runtime": 258038.6163,
+    "train_samples": 196741,
+    "train_samples_per_second": 0.596
+}

v3.0/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ed6b9297b9d49f900b09f3be8454fdf14fe0bf663a49aae7ff3247892738017
+size 2415

v3.0/vocab.json

@@ -0,0 +1 @@
+{"<unk>": 0, "<pad>": 1, "a": 2, "e": 3, "i": 4, "o": 5, "u": 6, "y": 7, "b": 8, "c": 9, "d": 10, "f": 11, "g": 12, "h": 13, "j": 14, "k": 15, "l": 16, "m": 17, "n": 18, "p": 19, "q": 20, "r": 21, "s": 22, "t": 23, "v": 24, "w": 25, "x": 26, "z": 27, "à": 28, "â": 29, "æ": 30, "ç": 31, "è": 32, "é": 33, "ê": 34, "ë": 35, "î": 36, "ï": 37, "ô": 38, "œ": 39, "ù": 40, "û": 41, "ü": 42, "ÿ": 43, "'": 44, "-": 45, "|": 46}