Training in progress, step 100

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 37,
+  "<s>": 36
+}

config.json

@@ -0,0 +1,116 @@
+{
+  "_name_or_path": "jonatasgrosman/wav2vec2-large-xlsr-53-russian",
+  "activation_dropout": 0.05,
+  "adapter_attn_dim": null,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "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": true,
+  "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": 0.05,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.05,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.05,
+  "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_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_min_space": 1,
+  "mask_time_other": 0.0,
+  "mask_time_prob": 0.05,
+  "mask_time_selection": "static",
+  "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": 35,
+  "proj_codevector_dim": 768,
+  "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": "4.44.2",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 39,
+  "xvector_output_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:857db45ab02e8b510e2ed94022a7f83af6e0d9ad719d58a48d742690a5f373bb
+size 1261967380

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": false,
+  "sampling_rate": 16000
+}

runs/Oct12_06-00-56_d5b9ba6f9988/events.out.tfevents.1728712857.d5b9ba6f9988.1388.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f73a98bdc76f53141dd3a92bcb6ce879dd59b72bfd735728767eca1fcb791db
+size 6784

runs/Oct12_06-22-00_d5b9ba6f9988/events.out.tfevents.1728714122.d5b9ba6f9988.1388.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d89c0edc4df860753be1598e9e4267199ec7e4ac9452e7b0de85a28008ef1593
+size 4184

runs/Oct12_06-23-41_d5b9ba6f9988/events.out.tfevents.1728714222.d5b9ba6f9988.1388.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84cd64c95a7fb5bc854109507e479ad5194c75c9d9cf99a8d1f68dcf9699d0a5
+size 4184

runs/Oct12_06-27-03_d5b9ba6f9988/events.out.tfevents.1728714424.d5b9ba6f9988.11850.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2da8c284de97eba2936846badf9d83e8e6138d8e3403af4fa919cf5be631d71
+size 7915

runs/Oct12_06-30-01_d5b9ba6f9988/events.out.tfevents.1728714602.d5b9ba6f9988.11850.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23b696ab6eb381db835b62b8947a1344ab8b0129ae1e59c883f5c8d432bb21a0
+size 7014

runs/Oct12_06-30-17_d5b9ba6f9988/events.out.tfevents.1728714618.d5b9ba6f9988.11850.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8127c12210519e208b94291195bb27521eeaa4c5e5957bfd4d0376a8cb646122
+size 7013

runs/Oct12_06-30-34_d5b9ba6f9988/events.out.tfevents.1728714635.d5b9ba6f9988.11850.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63cc283284e52ceb9dbffed76bb91c49431f2e6b5c5842c1318c3c3f90419e1e
+size 7012

runs/Oct12_06-30-49_d5b9ba6f9988/events.out.tfevents.1728714650.d5b9ba6f9988.11850.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e200d7b16a7d2445fdf373c72badc6cd39009af6f9dd426ef8115638a0b4c25b
+size 11257

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,48 @@
+{
+  "added_tokens_decoder": {
+    "34": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "35": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "36": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "37": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "processor_class": "Wav2Vec2Processor",
+  "replace_word_delimiter_char": " ",
+  "target_lang": 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:cd225bc68b563f78bcc03e9a9441f51a08f581c1a48b85c9e20cfda4e8b03706
+size 5176

vocab.json

@@ -0,0 +1,38 @@
+{
+  "[PAD]": 35,
+  "[UNK]": 34,
+  "|": 33,
+  "а": 0,
+  "б": 1,
+  "в": 2,
+  "г": 3,
+  "д": 4,
+  "е": 5,
+  "ж": 7,
+  "з": 8,
+  "и": 9,
+  "й": 10,
+  "к": 11,
+  "л": 12,
+  "м": 13,
+  "н": 14,
+  "о": 15,
+  "п": 16,
+  "р": 17,
+  "с": 18,
+  "т": 19,
+  "у": 20,
+  "ф": 21,
+  "х": 22,
+  "ц": 23,
+  "ч": 24,
+  "ш": 25,
+  "щ": 26,
+  "ъ": 27,
+  "ы": 28,
+  "ь": 29,
+  "э": 30,
+  "ю": 31,
+  "я": 32,
+  "ё": 6
+}