Training in progress, epoch 1

config.json

@@ -0,0 +1,115 @@
+{
+  "_name_or_path": "mujadid-syahbana/whisper-small-qur-base",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "apply_spec_augment": false,
+  "architectures": [
+    "WhisperForAudioClassification"
+  ],
+  "attention_dropout": 0.0,
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "classifier_proj_size": 256,
+  "d_model": 512,
+  "decoder_attention_heads": 8,
+  "decoder_ffn_dim": 2048,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 50258,
+  "dropout": 0.0,
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 2048,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 50257,
+  "finetuning_task": "audio-classification",
+  "forced_decoder_ids": null,
+  "id2label": {
+    "0": "alif",
+    "1": "seen",
+    "10": "wao",
+    "11": "kaif",
+    "12": "duad",
+    "13": "faa",
+    "14": "tua",
+    "15": "suad",
+    "16": "ba",
+    "17": "noon",
+    "18": "yaa",
+    "19": "hha",
+    "2": "zua",
+    "20": "hamzah",
+    "21": "sheen",
+    "22": "meem",
+    "23": "quaf",
+    "24": "zhal",
+    "25": "sa",
+    "26": "jeem",
+    "27": "aain",
+    "28": "zaa",
+    "3": "ta",
+    "4": "kha",
+    "5": "dal",
+    "6": "haa",
+    "7": "laam",
+    "8": "raa",
+    "9": "ghain"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "aain": "27",
+    "alif": "0",
+    "ba": "16",
+    "dal": "5",
+    "duad": "12",
+    "faa": "13",
+    "ghain": "9",
+    "haa": "6",
+    "hamzah": "20",
+    "hha": "19",
+    "jeem": "26",
+    "kaif": "11",
+    "kha": "4",
+    "laam": "7",
+    "meem": "22",
+    "noon": "17",
+    "quaf": "23",
+    "raa": "8",
+    "sa": "25",
+    "seen": "1",
+    "sheen": "21",
+    "suad": "15",
+    "ta": "3",
+    "tua": "14",
+    "wao": "10",
+    "yaa": "18",
+    "zaa": "28",
+    "zhal": "24",
+    "zua": "2"
+  },
+  "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": 0.05,
+  "max_length": 448,
+  "max_source_positions": 1500,
+  "max_target_positions": 448,
+  "median_filter_width": 7,
+  "model_type": "whisper",
+  "num_hidden_layers": 6,
+  "num_mel_bins": 80,
+  "pad_token_id": 50257,
+  "scale_embedding": false,
+  "suppress_tokens": [],
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.0.dev0",
+  "use_cache": true,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51865
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24cc56fd64b5518197381a0e7b48c8aca92f7b2ba6ce18d1e1b7db8761d4873a
+size 82928036

preprocessor_config.json

@@ -0,0 +1,14 @@
+{
+  "chunk_length": 30,
+  "feature_extractor_type": "WhisperFeatureExtractor",
+  "feature_size": 80,
+  "hop_length": 160,
+  "n_fft": 400,
+  "n_samples": 480000,
+  "nb_max_frames": 3000,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "WhisperProcessor",
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}

runs/Nov06_14-09-09_202e33c68888/events.out.tfevents.1699279757.202e33c68888.642.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d047c25232897e45dd45b5339840242740600f16c588b0a4f69a4301b08f6a8a
+size 6502

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba04a5b5cf58e4af1aa8726a6fbfdda9f320cbe569df983ff4a1b9f5c478cade
+size 4600