Training in progress, step 1000

config.json

@@ -1,6 +1,6 @@
 {
-  "_name_or_path": "facebook/wav2vec2-base",
-  "activation_dropout": 0.0,
+  "_name_or_path": "jonatasgrosman/wav2vec2-large-xlsr-53-french",
+  "activation_dropout": 0.05,
   "adapter_attn_dim": null,
   "adapter_kernel_size": 3,
   "adapter_stride": 2,
@@ -14,7 +14,7 @@
   "classifier_proj_size": 256,
   "codevector_dim": 256,
   "contrastive_logits_temperature": 0.1,
-  "conv_bias": false,
+  "conv_bias": true,
   "conv_dim": [
     512,
     512,
@@ -43,23 +43,23 @@
     2
   ],
   "ctc_loss_reduction": "mean",
-  "ctc_zero_infinity": false,
+  "ctc_zero_infinity": true,
   "diversity_loss_weight": 0.1,
-  "do_stable_layer_norm": false,
+  "do_stable_layer_norm": true,
   "eos_token_id": 2,
   "feat_extract_activation": "gelu",
-  "feat_extract_norm": "group",
-  "feat_proj_dropout": 0.1,
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "layer",
+  "feat_proj_dropout": 0.05,
   "feat_quantizer_dropout": 0.0,
   "final_dropout": 0.0,
-  "freeze_feat_extract_train": true,
   "hidden_act": "gelu",
-  "hidden_dropout": 0.1,
-  "hidden_size": 768,
+  "hidden_dropout": 0.05,
+  "hidden_size": 1024,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "intermediate_size": 4096,
   "layer_norm_eps": 1e-05,
-  "layerdrop": 0.0,
+  "layerdrop": 0.05,
   "mask_channel_length": 10,
   "mask_channel_min_space": 1,
   "mask_channel_other": 0.0,
@@ -75,18 +75,16 @@
   "mask_time_prob": 0.05,
   "mask_time_selection": "static",
   "model_type": "wav2vec2",
-  "no_mask_channel_overlap": false,
-  "no_mask_time_overlap": false,
   "num_adapter_layers": 3,
-  "num_attention_heads": 12,
+  "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": 12,
+  "num_hidden_layers": 24,
   "num_negatives": 100,
-  "output_hidden_size": 768,
+  "output_hidden_size": 1024,
   "pad_token_id": 0,
   "proj_codevector_dim": 256,
   "tdnn_dilation": [
@@ -113,6 +111,6 @@
   "torch_dtype": "float32",
   "transformers_version": "4.40.0",
   "use_weighted_layer_sum": false,
-  "vocab_size": 32,
+  "vocab_size": 59,
   "xvector_output_dim": 512
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:083c207596f09087e4e4225f1b210f08def25ecfe79aa1cb2528f2b9d808a2fa
-size 377611120
+oid sha256:4024c2850c162fed23998276ecce1bc57a308eff401efaee1daaf72eb0dbcbbb
+size 1262049380

preprocessor_config.json

@@ -5,6 +5,6 @@
   "padding_side": "right",
   "padding_value": 0.0,
   "processor_class": "Wav2Vec2Processor",
-  "return_attention_mask": false,
+  "return_attention_mask": true,
   "sampling_rate": 16000
 }

runs/Apr25_03-27-59_038ab5dc6aba/events.out.tfevents.1714015684.038ab5dc6aba.1196.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67830c205d585f0188d690dc73ea4f2d0af5b48053586de0e3e284ac4a7641ae
+size 15082

tokenizer_config.json

@@ -36,13 +36,11 @@
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
   "do_lower_case": false,
-  "do_normalize": true,
   "eos_token": "</s>",
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
   "processor_class": "Wav2Vec2Processor",
   "replace_word_delimiter_char": " ",
-  "return_attention_mask": false,
   "target_lang": null,
   "tokenizer_class": "Wav2Vec2CTCTokenizer",
   "unk_token": "<unk>",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7aedda861a5cc056ba2791db7976040f87f3c776ac997dacd3bc7edbfafca500
+oid sha256:e153b4077de99cb948ab5adbff75dae0f2679b6ddc81daa829bcd5c84581b63f
 size 4984

vocab.json

@@ -1,34 +1,61 @@
 {
-  "'": 27,
+  "'": 5,
+  "-": 6,
   "</s>": 2,
   "<pad>": 0,
   "<s>": 1,
   "<unk>": 3,
-  "A": 7,
-  "B": 24,
-  "C": 19,
-  "D": 14,
-  "E": 5,
-  "F": 20,
-  "G": 21,
-  "H": 11,
-  "I": 10,
-  "J": 29,
-  "K": 26,
-  "L": 15,
-  "M": 17,
-  "N": 9,
-  "O": 8,
-  "P": 23,
-  "Q": 30,
-  "R": 13,
-  "S": 12,
-  "T": 6,
-  "U": 16,
-  "V": 25,
-  "W": 18,
-  "X": 28,
-  "Y": 22,
-  "Z": 31,
-  "|": 4
+  "a": 7,
+  "b": 8,
+  "c": 9,
+  "d": 10,
+  "e": 11,
+  "f": 12,
+  "g": 13,
+  "h": 14,
+  "i": 15,
+  "j": 16,
+  "k": 17,
+  "l": 18,
+  "m": 19,
+  "n": 20,
+  "o": 21,
+  "p": 22,
+  "q": 23,
+  "r": 24,
+  "s": 25,
+  "t": 26,
+  "u": 27,
+  "v": 28,
+  "w": 29,
+  "x": 30,
+  "y": 31,
+  "z": 32,
+  "|": 4,
+  "à": 33,
+  "á": 34,
+  "â": 35,
+  "ä": 36,
+  "ç": 37,
+  "è": 38,
+  "é": 39,
+  "ê": 40,
+  "ë": 41,
+  "í": 42,
+  "î": 43,
+  "ï": 44,
+  "ñ": 45,
+  "ó": 46,
+  "ô": 47,
+  "ö": 48,
+  "ù": 49,
+  "ú": 50,
+  "û": 51,
+  "ü": 52,
+  "ć": 53,
+  "č": 54,
+  "ō": 55,
+  "œ": 56,
+  "š": 57,
+  "ș": 58
 }