Training in progress, step 10

.gitignore

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

added_tokens.json

@@ -0,0 +1 @@
+{"<s>": 32, "</s>": 33}

config.json

@@ -0,0 +1,121 @@
+{
+  "_name_or_path": "/content/gdrive/MyDrive/02 - bzh_translater/2_SpeechToText/model/wav2vec-xsl-r-300m",
+  "activation_dropout": 0.0,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForSpeechClassification"
+  ],
+  "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": 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": 0.1,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "finetuning_task": "wav2vec2_clf",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "Gwenedeg",
+    "1": "Kerneveg",
+    "2": "Leoneg"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "Gwenedeg": 0,
+    "Kerneveg": 1,
+    "Leoneg": 2
+  },
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "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": 0.075,
+  "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": 31,
+  "pooling_mode": "mean",
+  "problem_type": "single_label_classification",
+  "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": "4.11.3",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32,
+  "xvector_output_dim": 512
+}

preprocessor_config.json

@@ -0,0 +1,9 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c08156e3d70fe2cfc1e43f291cd8abc6d7e86ce789eac79187c1cd3517e3f314
+size 1266135149

runs/Nov27_17-19-51_520d9cc1930d/1669569601.9047437/events.out.tfevents.1669569601.520d9cc1930d.78.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fce440e91c254d6ec5e58af5d85f08e1c9defe5d2c4186d6b9617a30ea9faeb2
+size 4558

runs/Nov27_17-19-51_520d9cc1930d/events.out.tfevents.1669569601.520d9cc1930d.78.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9c802696b36f3bf806a81dddb7d27774b3eaa4e52168870ffcceaf40a52afcb
+size 5350

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_lower_case": false, "word_delimiter_token": "|", "replace_word_delimiter_char": " ", "special_tokens_map_file": "/content/gdrive/MyDrive/02 - bzh_translater/2_SpeechToText/model/wav2vec-xsl-r-300m/special_tokens_map.json", "tokenizer_file": null, "name_or_path": "/content/gdrive/MyDrive/02 - bzh_translater/2_SpeechToText/model/wav2vec-xsl-r-300m", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fbc6c6f5f0175c621f267532c9ce8bf57806a0ae353bc746fc081226d5e3b6d
+size 2863

vocab.json

@@ -0,0 +1 @@
+{"r": 0, "e": 1, "o": 2, "h": 3, "f": 4, "l": 5, "w": 6, "s": 7, "v": 8, "j": 9, "n": 10, "a": 11, "u": 12, "x": 13, "d": 14, "k": 15, "g": 16, "i": 17, "t": 18, "ñ": 19, "b": 20, "y": 21, "p": 22, "ù": 23, "'": 24, "z": 25, "c": 27, "q": 28, "m": 29, "|": 26, "[UNK]": 30, "[PAD]": 31}