First version of the wav2vec2-large-xlsr-arabice model and tokenizer.

.gitattributes

@@ -13,4 +13,4 @@
 *.msgpack filter=lfs diff=lfs merge=lfs -text
 *.pb filter=lfs diff=lfs merge=lfs -text
 *.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text

all_results.json

@@ -0,0 +1,23 @@
+{
+    "epoch": 30.0,
+    "eval_loss": 1.1619502305984497,
+    "eval_mem_cpu_alloc_delta": 1765203650,
+    "eval_mem_cpu_peaked_delta": 70416270,
+    "eval_mem_gpu_alloc_delta": 0,
+    "eval_mem_gpu_peaked_delta": 5896910848,
+    "eval_runtime": 883.3879,
+    "eval_samples": 7622,
+    "eval_samples_per_second": 8.628,
+    "eval_wer": 0.6438685083419972,
+    "init_mem_cpu_alloc_delta": 620838,
+    "init_mem_cpu_peaked_delta": 18306,
+    "init_mem_gpu_alloc_delta": 1262070784,
+    "init_mem_gpu_peaked_delta": 0,
+    "train_mem_cpu_alloc_delta": 0,
+    "train_mem_cpu_peaked_delta": 0,
+    "train_mem_gpu_alloc_delta": 3788204544,
+    "train_mem_gpu_peaked_delta": 0,
+    "train_runtime": 115603.8298,
+    "train_samples": 21744,
+    "train_samples_per_second": 0.176
+}

config.json

@@ -0,0 +1,76 @@
+{
+  "_name_or_path": "facebook/wav2vec2-large-xlsr-53",
+  "activation_dropout": 0.055,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.094,
+  "bos_token_id": 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,
+  "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": 0.04,
+  "final_dropout": 0.0,
+  "gradient_checkpointing": true,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.047,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.041,
+  "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_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_space": 1,
+  "mask_time_other": 0.0,
+  "mask_time_prob": 0.082,
+  "mask_time_selection": "static",
+  "model_type": "wav2vec2",
+  "num_attention_heads": 16,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 24,
+  "pad_token_id": 76,
+  "transformers_version": "4.5.0.dev0",
+  "vocab_size": 77
+}

eval_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 30.0,
+    "eval_loss": 1.1619502305984497,
+    "eval_mem_cpu_alloc_delta": 1765203650,
+    "eval_mem_cpu_peaked_delta": 70416270,
+    "eval_mem_gpu_alloc_delta": 0,
+    "eval_mem_gpu_peaked_delta": 5896910848,
+    "eval_runtime": 883.3879,
+    "eval_samples": 7622,
+    "eval_samples_per_second": 8.628,
+    "eval_wer": 0.6438685083419972
+}

preprocessor_config.json

@@ -0,0 +1,8 @@
+{
+  "do_normalize": true,
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]"}

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": "|"}

train_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 30.0,
+    "init_mem_cpu_alloc_delta": 620838,
+    "init_mem_cpu_peaked_delta": 18306,
+    "init_mem_gpu_alloc_delta": 1262070784,
+    "init_mem_gpu_peaked_delta": 0,
+    "train_mem_cpu_alloc_delta": 0,
+    "train_mem_cpu_peaked_delta": 0,
+    "train_mem_gpu_alloc_delta": 3788204544,
+    "train_mem_gpu_peaked_delta": 0,
+    "train_runtime": 115603.8298,
+    "train_samples": 21744,
+    "train_samples_per_second": 0.176
+}

vocab.json

@@ -0,0 +1 @@
+{"t": 0, "ه": 1, "ح": 2, "؛": 3, "ى": 4, "ف": 5, "غ": 6, "ج": 7, "ع": 8, "چ": 9, ".": 10, "ﻻ": 11, "ٌ": 12, "e": 13, "ْ": 14, ":": 15, "،": 16, "خ": 17, "ئ": 18, "َ": 19, "ﺃ": 20, "ب": 21, "ڨ": 22, "أ": 23, "د": 24, "ا": 25, "ً": 26, ";": 27, "ذ": 28, "و": 29, "ة": 30, "-": 31, "_": 32, "ّ": 34, "\"": 35, "?": 36, "آ": 37, "ء": 38, "—": 39, "”": 40, "ش": 41, "“": 42, "ر": 43, "ٍ": 44, "ـ": 45, "ك": 46, "!": 47, "ي": 48, ",": 49, "ط": 50, "ھ": 51, "ز": 52, "م": 53, "ض": 54, "ِ": 55, "ؤ": 56, "ث": 57, "ُ": 58, "ق": 59, "ٰ": 60, "؟": 61, "ص": 62, "ۚ": 63, "g": 64, "ۖ": 65, "☭": 66, "ل": 67, "ی": 68, "ن": 69, "س": 70, "ظ": 71, "ک": 72, "ت": 73, "إ": 74, "|": 33, "[UNK]": 75, "[PAD]": 76}