Training in progress, step 100

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

added_tokens.json

@@ -0,0 +1 @@
+{"<s>": 44}

config.json

@@ -0,0 +1,86 @@
+{
+  "_name_or_path": "./wav2vec2-xls-r-300m-phoneme-sv",
+  "activation_dropout": 0.0,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 44,
+  "classifier_proj_size": 256,
+  "codevector_dim": 768,
+  "contrastive_logits_temperature": 0.1,
+  "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,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": true,
+  "eos_token_id": 41,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "layer",
+  "feat_proj_dropout": 0.0,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0,
+  "mask_feature_length": 64,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.1,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.3,
+  "model_type": "wav2vec2",
+  "num_adapter_layers": 3,
+  "num_attention_heads": 16,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 24,
+  "num_negatives": 100,
+  "output_hidden_size": 1024,
+  "pad_token_id": 43,
+  "proj_codevector_dim": 768,
+  "torch_dtype": "float32",
+  "transformers_version": "4.13.0.dev0",
+  "unk_token_id": 42,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 45
+}

preprocessor_config.json

@@ -0,0 +1,9 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0,
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:837f92c286ad5af3e28115544497abc025b9e54d04c807a58802e8cd528bf160
+size 1262108145

runs/Dec08_00-00-48_brutasse/1638921726.7681508/events.out.tfevents.1638921726.brutasse.2691.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ce63bc72700a94dcd940759eb9d33974dd41dc6b78e541ca76738bbab5bb514
+size 4706

runs/Dec08_00-00-48_brutasse/events.out.tfevents.1638921726.brutasse.2691.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98665eae0b63b3cc542d1464f82c28c319b3f41c2220a92d4e8a286102a743bc
+size 20189

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "<pad>", "do_phonemize": true, "phonemizer_lang": "en-us", "phonemizer_backend": "espeak", "special_tokens_map_file": "./special_tokens_map.json", "tokenizer_file": null, "name_or_path": "./wav2vec2-xls-r-300m-phoneme-sv", "word_delimiter_token": "|", "tokenizer_class": "Wav2Vec2PhonemeCTCTokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fb6802c28b521622527268ad3b2ea9e978871f682e405fc47672160c2c3fae6
+size 2927

vocab.json

@@ -0,0 +1 @@
+{"h": 0, "a": 1, "n": 2, "v": 3, "eː": 4, "t": 5, "ɛː": 6, "l": 7, "ɪ": 8, "ɛ": 9, "ɑː": 10, "d": 11, "s": 12, "ɔ": 13, "m": 14, "ə": 15, "r": 16, "iː": 17, "k": 18, "p": 19, "ʉ": 20, "f": 21, "yː": 22, "ɡ": 23, "øː": 24, "uː": 25, "j": 26, "b": 27, "œ": 28, "ɵ": 29, "sx": 30, "oː": 31, "ŋ": 32, "ɕ": 33, "y": 34, "kː": 35, "ʊ": 36, "ʃ": 37, "tː": 38, "ʂ": 39, "ɵː": 40, "</s>": 41, "<unk>": 42, "<pad>": 43}