Training in progress, step 1000

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 68,
+  "<s>": 67
+}

config.json

@@ -0,0 +1,82 @@
+{
+  "_name_or_path": "facebook/w2v-bert-2.0",
+  "activation_dropout": 0.0,
+  "adapter_act": "relu",
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": true,
+  "apply_spec_augment": false,
+  "architectures": [
+    "Wav2Vec2BertForCTC"
+  ],
+  "attention_dropout": 0.05,
+  "bos_token_id": 1,
+  "classifier_proj_size": 768,
+  "codevector_dim": 768,
+  "conformer_conv_dropout": 0.1,
+  "contrastive_logits_temperature": 0.1,
+  "conv_depthwise_kernel_size": 31,
+  "ctc_loss_reduction": "mean",
+  "ctc_zero_infinity": true,
+  "diversity_loss_weight": 0.1,
+  "eos_token_id": 2,
+  "feat_proj_dropout": 0.05,
+  "feat_quantizer_dropout": 0.0,
+  "feature_projection_input_dim": 160,
+  "final_dropout": 0.1,
+  "hidden_act": "swish",
+  "hidden_dropout": 0.05,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0,
+  "left_max_position_embeddings": 64,
+  "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,
+  "max_source_positions": 5000,
+  "model_type": "wav2vec2-bert",
+  "num_adapter_layers": 1,
+  "num_attention_heads": 16,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_hidden_layers": 24,
+  "num_negatives": 100,
+  "output_hidden_size": 1024,
+  "pad_token_id": 66,
+  "position_embeddings_type": "relative_key",
+  "proj_codevector_dim": 768,
+  "right_max_position_embeddings": 8,
+  "rotary_embedding_base": 10000,
+  "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": "4.48.1",
+  "use_intermediate_ffn_before_adapter": false,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 69,
+  "xvector_output_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:640ae09feff8e775b8a6477e98706b3ca6e93bfc17bebcf2512e3b873c2a8736
+size 2423097460

preprocessor_config.json

@@ -0,0 +1,11 @@
+{
+  "feature_extractor_type": "SeamlessM4TFeatureExtractor",
+  "feature_size": 80,
+  "num_mel_bins": 80,
+  "padding_side": "right",
+  "padding_value": 1,
+  "processor_class": "Wav2Vec2BertProcessor",
+  "return_attention_mask": true,
+  "sampling_rate": 16000,
+  "stride": 2
+}

runs/Jul18_00-07-43_gf-asr-training-2a100/events.out.tfevents.1752797745.gf-asr-training-2a100.244221.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32737232e315cd7e21d11655998c83c45fa24f15d3e0141a408cdab3fb493519
+size 217298

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": {
+    "65": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "66": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "67": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "68": {
+      "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": "Wav2Vec2BertProcessor",
+  "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:f1dcc7255b110c382a265f4d2184612e2af0437933f9352b90b28cef7023e184
+size 5841

vocab.json

@@ -0,0 +1,69 @@
+{
+  "'": 1,
+  "-": 2,
+  "0": 3,
+  "1": 4,
+  "2": 5,
+  "3": 6,
+  "4": 7,
+  "5": 8,
+  "6": 9,
+  "7": 10,
+  "8": 11,
+  "9": 12,
+  "[PAD]": 66,
+  "[UNK]": 65,
+  "a": 13,
+  "b": 14,
+  "c": 15,
+  "d": 16,
+  "e": 17,
+  "f": 18,
+  "g": 19,
+  "h": 20,
+  "i": 21,
+  "j": 22,
+  "k": 23,
+  "l": 24,
+  "m": 25,
+  "n": 26,
+  "o": 27,
+  "p": 28,
+  "q": 29,
+  "r": 30,
+  "s": 31,
+  "t": 32,
+  "u": 33,
+  "v": 34,
+  "w": 35,
+  "x": 36,
+  "y": 37,
+  "z": 38,
+  "|": 0,
+  "à": 39,
+  "á": 40,
+  "è": 41,
+  "é": 42,
+  "ì": 43,
+  "í": 44,
+  "ñ": 45,
+  "ò": 46,
+  "ó": 47,
+  "ù": 48,
+  "ú": 49,
+  "ā": 50,
+  "ē": 51,
+  "ń": 52,
+  "ǹ": 53,
+  "̀": 54,
+  "́": 55,
+  "̄": 56,
+  "̣": 57,
+  "ṅ": 58,
+  "ạ": 59,
+  "ẹ": 60,
+  "ị": 61,
+  "ọ": 62,
+  "ụ": 63,
+  "’": 64
+}