Training in progress, step 250

.gitignore

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

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 66,
+  "<s>": 65
+}

config.json

@@ -0,0 +1,107 @@
+{
+  "_name_or_path": "aware-ai/wav2vec2-xls-r-1b-5gram-german",
+  "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": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 1024,
+  "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": 2,
+  "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": 1280,
+  "initializer_range": 0.02,
+  "intermediate_size": 5120,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0,
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.0,
+  "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": 48,
+  "num_negatives": 100,
+  "output_hidden_size": 1280,
+  "pad_token_id": 64,
+  "proj_codevector_dim": 1024,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.21.1",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 67,
+  "xvector_output_dim": 512
+}

preprocessor_config.json

@@ -0,0 +1,10 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "Wav2Vec2Processor",
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e6580d384d6731b5b33603f9c5478c5e9d30e44959bacdab047896d6d71f88a
+size 3850602867

runs/Sep06_18-55-09_aware/1662483894.6907737/events.out.tfevents.1662483894.aware.365573.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad19937e3bee6422f15775e0e148019f51b43f56004588aac7f56387fa321a3b
+size 5707

runs/Sep06_18-55-09_aware/events.out.tfevents.1662483894.aware.365573.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b7708e2ac73ddc94ef57b023450f9158ba3b8eee73225ff2a326ed6f1be85b0
+size 6475

runs/Sep06_19-20-42_aware/1662484888.8305564/events.out.tfevents.1662484888.aware.481052.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e1574e21df0c3c4dbec98f8ad341a1c8845b8e9e96cf7585811c5e481985ae1
+size 5707

runs/Sep06_19-20-42_aware/events.out.tfevents.1662484888.aware.481052.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27ff8684b4b1d333b78fba57a44e7e4567ae12e104d86e0fe30ffa014872cd7a
+size 5396

runs/Sep06_19-23-44_aware/1662485067.7447095/events.out.tfevents.1662485067.aware.491449.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d907e520fc68b237d47a213b17356201d44e0e70c9e9b760a5fec65149bf59a
+size 5707

runs/Sep06_19-23-44_aware/events.out.tfevents.1662485067.aware.491449.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff60f0215400b749b5cd20ceb5397a0385a5d8bac42e60fa94a2b11e97ca4ce6
+size 44111

special_tokens_map.json

@@ -0,0 +1,134 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token": "<s>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "name_or_path": "wav2vec2-xls-r-1b-german",
+  "pad_token": "[PAD]",
+  "processor_class": "Wav2Vec2Processor",
+  "replace_word_delimiter_char": " ",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d77bf8a0a4c4c625e4b93ce1aad13c1346a8cf964459a1119991cfe7cb854c1e
+size 3567

vocab.json

@@ -0,0 +1,67 @@
+{
+  "!": 1,
+  ",": 2,
+  ".": 3,
+  "?": 4,
+  "A": 5,
+  "B": 6,
+  "C": 7,
+  "D": 8,
+  "E": 9,
+  "F": 10,
+  "G": 11,
+  "H": 12,
+  "I": 13,
+  "J": 14,
+  "K": 15,
+  "L": 16,
+  "M": 17,
+  "N": 18,
+  "O": 19,
+  "P": 20,
+  "Q": 21,
+  "R": 22,
+  "S": 23,
+  "T": 24,
+  "U": 25,
+  "V": 26,
+  "W": 27,
+  "X": 28,
+  "Y": 29,
+  "Z": 30,
+  "[PAD]": 64,
+  "[UNK]": 63,
+  "a": 31,
+  "b": 32,
+  "c": 33,
+  "d": 34,
+  "e": 35,
+  "f": 36,
+  "g": 37,
+  "h": 38,
+  "i": 39,
+  "j": 40,
+  "k": 41,
+  "l": 42,
+  "m": 43,
+  "n": 44,
+  "o": 45,
+  "p": 46,
+  "q": 47,
+  "r": 48,
+  "s": 49,
+  "t": 50,
+  "u": 51,
+  "v": 52,
+  "w": 53,
+  "x": 54,
+  "y": 55,
+  "z": 56,
+  "|": 0,
+  "Ä": 57,
+  "Ö": 58,
+  "Ü": 59,
+  "ä": 60,
+  "ö": 61,
+  "ü": 62
+}