Training in progress, step 400

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 74,
+  "<s>": 73
+}

config.json

@@ -0,0 +1,119 @@
+{
+  "activation_dropout": 0.0,
+  "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": 256,
+  "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,
+  "forced_decoder_ids": null,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "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",
+  "max_length": 512,
+  "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": 72,
+  "proj_codevector_dim": 256,
+  "suppress_tokens": [],
+  "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": "4.52.4",
+  "use_cache": false,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 73,
+  "xvector_output_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57d828db856121860d6a26b87c82c54ea5839f55a0cd7e9fe79b27aac3c5e6ba
+size 1262106780

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
+}

runs/Jun21_03-56-37_37eff2c853c1/events.out.tfevents.1750478307.37eff2c853c1.1979.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b45da525c6f8b323fad1f4f6f80b11baf3647e44d88c0ad7ba6a983354800fb
+size 404

runs/Jun21_04-04-03_37eff2c853c1/events.out.tfevents.1750478651.37eff2c853c1.1979.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94d0944fa31760bcc9c08d7fd112eb23acaa98989206333d8f7474fb0a927526
+size 10291

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,49 @@
+{
+  "added_tokens_decoder": {
+    "71": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "72": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "73": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "74": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "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 sha256:68f74676ad6c0edf2791a7ebda1e481a93967ba0862a08c86965eeffe6ca22bd
+size 5304

vocab.json

@@ -0,0 +1,75 @@
+{
+  "[PAD]": 72,
+  "[UNK]": 71,
+  "|": 35,
+  "ក": 68,
+  "ខ": 70,
+  "គ": 67,
+  "ឃ": 58,
+  "ង": 3,
+  "ច": 38,
+  "ឆ": 14,
+  "ជ": 53,
+  "ឈ": 4,
+  "ញ": 49,
+  "ដ": 16,
+  "ឋ": 13,
+  "ឌ": 22,
+  "ឍ": 9,
+  "ណ": 8,
+  "ត": 18,
+  "ថ": 46,
+  "ទ": 55,
+  "ធ": 59,
+  "ន": 45,
+  "ប": 34,
+  "ផ": 51,
+  "ព": 23,
+  "ភ": 47,
+  "ម": 62,
+  "យ": 37,
+  "រ": 26,
+  "ល": 17,
+  "វ": 1,
+  "ស": 7,
+  "ហ": 25,
+  "ឡ": 33,
+  "អ": 60,
+  "ឥ": 40,
+  "ឧ": 11,
+  "ឪ": 21,
+  "ឫ": 66,
+  "ឬ": 41,
+  "ឭ": 31,
+  "ឮ": 24,
+  "ឯ": 48,
+  "ឱ": 10,
+  "ា": 69,
+  "ិ": 0,
+  "ី": 50,
+  "ឹ": 65,
+  "ឺ": 52,
+  "ុ": 19,
+  "ូ": 64,
+  "ួ": 44,
+  "ើ": 43,
+  "ឿ": 63,
+  "ៀ": 6,
+  "េ": 39,
+  "ែ": 12,
+  "ៃ": 20,
+  "ោ": 30,
+  "ៅ": 15,
+  "ំ": 42,
+  "ះ": 2,
+  "ៈ": 27,
+  "៉": 61,
+  "៊": 5,
+  "់": 54,
+  "៌": 36,
+  "៍": 32,
+  "៎": 29,
+  "៏": 57,
+  "័": 28,
+  "្": 56
+}