Training in progress, epoch 10

config.json

@@ -0,0 +1,111 @@
+{
+  "_name_or_path": "tarteel-ai/whisper-base-ar-quran",
+  "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,
+  "forced_decoder_ids": null,
+  "id2label": {
+    "0": "01_A",
+    "1": "02_Ba",
+    "2": "03_Ta",
+    "3": "04_Tsa",
+    "4": "05_Ja",
+    "5": "06_Hha",
+    "6": "07_Kha",
+    "7": "08_Da",
+    "8": "09_Dza",
+    "9": "10_Ro",
+    "10": "11_Za",
+    "11": "12_Sa",
+    "12": "13_Sya",
+    "13": "14_Sho",
+    "14": "15_Dho",
+    "15": "16_Tho",
+    "16": "17_Zho",
+    "17": "18_Ain",
+    "18": "19_Gho",
+    "19": "20_Fa",
+    "20": "21_Qo",
+    "21": "22_Ka",
+    "22": "23_La",
+    "23": "24_Ma",
+    "24": "25_Na",
+    "25": "26_Ha",
+    "26": "27_Wa",
+    "27": "28_Ya"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "01_A": 0,
+    "02_Ba": 1,
+    "03_Ta": 2,
+    "04_Tsa": 3,
+    "05_Ja": 4,
+    "06_Hha": 5,
+    "07_Kha": 6,
+    "08_Da": 7,
+    "09_Dza": 8,
+    "10_Ro": 9,
+    "11_Za": 10,
+    "12_Sa": 11,
+    "13_Sya": 12,
+    "14_Sho": 13,
+    "15_Dho": 14,
+    "16_Tho": 15,
+    "17_Zho": 16,
+    "18_Ain": 17,
+    "19_Gho": 18,
+    "20_Fa": 19,
+    "21_Qo": 20,
+    "22_Ka": 21,
+    "23_La": 22,
+    "24_Ma": 23,
+    "25_Na": 24,
+    "26_Ha": 25,
+    "27_Wa": 26,
+    "28_Ya": 27
+  },
+  "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": 1024,
+  "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,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.2",
+  "use_cache": false,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51865
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9052d831ea5dc7f4a60e5fda82476f59ac921a27d73cdc295427a44d30ea2e4b
+size 82927008

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/Dec01_23-36-22_5c12ed67cd21/events.out.tfevents.1733096190.5c12ed67cd21.910.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4820bc179c9a082ec6c5256b3cea0c6387c3aecdb2495f6c790705c1408e58d7
+size 970909

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff62fa66999b71dc8d8d647921ee3b945b5f52714a2b2a0ef0901babdb39282d
+size 5304