Training in progress, step 8000

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 88,
+  "<s>": 87
+}

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": 86,
+  "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": 89,
+  "xvector_output_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f24533454ca397dd5f1c3f71ff342b706be8c90c16d4a39763a986f49644a39
+size 2423179460

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/Apr23_17-35-24_synvoices-hausa-2/events.out.tfevents.1745429967.synvoices-hausa-2.5480.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e314bb4ecfcaecd7b1713eff1134f843200a0ca7b809b371380561a8430063a
+size 1697065

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": {
+    "85": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "86": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "87": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "88": {
+      "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:b907db4aab216e92c06e3b670d32ff88ab0f57b52b26fa71c15b1cb402de52c4
+size 5432

vocab.json

@@ -0,0 +1,89 @@
+{
+  "&": 1,
+  "'": 2,
+  "*": 3,
+  "+": 4,
+  "-": 5,
+  "/": 6,
+  "0": 7,
+  "1": 8,
+  "2": 9,
+  "3": 10,
+  "4": 11,
+  "5": 12,
+  "6": 13,
+  "7": 14,
+  "8": 15,
+  "9": 16,
+  "=": 17,
+  ">": 18,
+  "[PAD]": 86,
+  "[UNK]": 85,
+  "\\": 19,
+  "_": 20,
+  "`": 21,
+  "a": 22,
+  "b": 23,
+  "c": 24,
+  "d": 25,
+  "e": 26,
+  "f": 27,
+  "g": 28,
+  "h": 29,
+  "i": 30,
+  "j": 31,
+  "k": 32,
+  "l": 33,
+  "m": 34,
+  "n": 35,
+  "o": 36,
+  "p": 37,
+  "q": 38,
+  "r": 39,
+  "s": 40,
+  "t": 41,
+  "u": 42,
+  "v": 43,
+  "w": 44,
+  "x": 45,
+  "y": 46,
+  "z": 47,
+  "|": 0,
+  "à": 48,
+  "á": 49,
+  "ã": 50,
+  "è": 51,
+  "é": 52,
+  "ì": 53,
+  "í": 54,
+  "ñ": 55,
+  "ò": 56,
+  "ô": 57,
+  "õ": 58,
+  "ù": 59,
+  "ú": 60,
+  "ý": 61,
+  "ā": 62,
+  "ď": 63,
+  "ē": 64,
+  "ı": 65,
+  "ō": 66,
+  "ş": 67,
+  "ū": 68,
+  "ŭ": 69,
+  "ž": 70,
+  "ƙ": 71,
+  "ƴ": 72,
+  "ǹ": 73,
+  "ɓ": 74,
+  "ɗ": 75,
+  "ʼ": 76,
+  "̀": 77,
+  "ṣ": 78,
+  "ẹ": 79,
+  "ọ": 80,
+  "—": 81,
+  "‘": 82,
+  "’": 83,
+  "…": 84
+}