Training in progress, step 500

.gitignore

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

added_tokens.json

@@ -0,0 +1 @@
+{"<s>": 40, "</s>": 41}

config.json

@@ -0,0 +1,108 @@
+{
+  "_name_or_path": "facebook/wav2vec2-xls-r-300m",
+  "activation_dropout": 0.1,
+  "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": 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": 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": 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": 0.25,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.75,
+  "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": 39,
+  "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": "4.17.0.dev0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 42,
+  "xvector_output_dim": 512,
+  "zero_infinity": true
+}

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:afb0e7ffda879f5270fa52dc156834e2d5ad06c7ae971e1b62cca619780de3ee
+size 1262095857

runs/Feb04_08-09-55_job-699ba53c-fea9-4eb2-81af-a97f440eaa45/1643962246.51635/events.out.tfevents.1643962246.job-699ba53c-fea9-4eb2-81af-a97f440eaa45.1195751.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf44a0386d13a3a5c76f2c5eede59e843c104f3ddf914cc0e0c7e7dd67e89e67
+size 4802

runs/Feb04_08-09-55_job-699ba53c-fea9-4eb2-81af-a97f440eaa45/events.out.tfevents.1643962246.job-699ba53c-fea9-4eb2-81af-a97f440eaa45.1195751.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8916ecf2a48c299a0db37548cdc0cd242dd4884bd0223d15903b1ed9e0a37f61
+size 4756

runs/Feb04_08-11-34_job-699ba53c-fea9-4eb2-81af-a97f440eaa45/1643962316.8321793/events.out.tfevents.1643962316.job-699ba53c-fea9-4eb2-81af-a97f440eaa45.1196512.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66f4527d4c04c47dff47f28aef97ddb037cf0cbdc381d848394f67e43ae40283
+size 4802

runs/Feb04_08-11-34_job-699ba53c-fea9-4eb2-81af-a97f440eaa45/events.out.tfevents.1643962316.job-699ba53c-fea9-4eb2-81af-a97f440eaa45.1196512.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5847b786888c124410f0f6c6ce8dd49aeb214b12641a14b2ab33e51e6825b959
+size 4755

runs/Feb04_08-12-46_job-699ba53c-fea9-4eb2-81af-a97f440eaa45/1643962413.1460874/events.out.tfevents.1643962413.job-699ba53c-fea9-4eb2-81af-a97f440eaa45.1197052.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e76136d34090929026319aaababd27cb091939131cdf911b80869b9d515e25c0
+size 4802

runs/Feb04_08-12-46_job-699ba53c-fea9-4eb2-81af-a97f440eaa45/events.out.tfevents.1643962413.job-699ba53c-fea9-4eb2-81af-a97f440eaa45.1197052.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8eccc50538532c903f4c710a57826e15f6c166afe3df42e36ef68baef2a88323
+size 4755

runs/Feb04_08-15-32_job-699ba53c-fea9-4eb2-81af-a97f440eaa45/1643962578.6550806/events.out.tfevents.1643962578.job-699ba53c-fea9-4eb2-81af-a97f440eaa45.1198181.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d46edffaef664e941143ea163009f6999a4f0f06578a39f8ea68294a1dbda15
+size 4802

runs/Feb04_08-15-32_job-699ba53c-fea9-4eb2-81af-a97f440eaa45/events.out.tfevents.1643962578.job-699ba53c-fea9-4eb2-81af-a97f440eaa45.1198181.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69a9e1de9ffeb4b5da7926b30a28e861ee9748f1f59af351798e8c0db691da34
+size 5856

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}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"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_lower_case": false, "word_delimiter_token": "|", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "./xls-r-kyrgiz-cv8", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cde060aa868bd66f6b2774ce16ec7877e122267f0549334cd1553b0d3ad50ad5
+size 3055

vocab.json

@@ -0,0 +1 @@
+{"а": 1, "б": 2, "в": 3, "г": 4, "д": 5, "е": 6, "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": 33, "ң": 34, "ү": 35, "ӊ": 36, "ө": 37, "|": 0, "[UNK]": 38, "[PAD]": 39}