End of training

README.md

@@ -0,0 +1,85 @@
+---
+language:
+- ar
+license: apache-2.0
+base_model: tarteel-ai/whisper-base-ar-quran
+tags:
+- generated_from_trainer
+datasets:
+- mozilla-foundation/common_voice_11_0
+metrics:
+- wer
+model-index:
+- name: Whisper Small Ar - raghad
+  results:
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: Zolfa Dataset
+      type: mozilla-foundation/common_voice_11_0
+      args: 'config: ar, split: test'
+    metrics:
+    - name: Wer
+      type: wer
+      value: 10.344827586206897
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# Whisper Small Ar - raghad
+
+This model is a fine-tuned version of [tarteel-ai/whisper-base-ar-quran](https://huggingface.co/tarteel-ai/whisper-base-ar-quran) on the Zolfa Dataset dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0195
+- Wer: 10.3448
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-05
+- train_batch_size: 16
+- eval_batch_size: 2
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Wer     |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|
+| 0.0045        | 1.0   | 21   | 0.0047          | 0.0     |
+| 0.0015        | 2.0   | 42   | 0.0220          | 10.3448 |
+| 0.0012        | 3.0   | 63   | 0.0223          | 10.3448 |
+| 0.0006        | 4.0   | 84   | 0.0161          | 10.3448 |
+| 0.0004        | 5.0   | 105  | 0.0199          | 10.3448 |
+| 0.0003        | 6.0   | 126  | 0.0187          | 10.3448 |
+| 0.0002        | 7.0   | 147  | 0.0181          | 10.3448 |
+| 0.0003        | 8.0   | 168  | 0.0195          | 10.3448 |
+| 0.0002        | 9.0   | 189  | 0.0193          | 10.3448 |
+| 0.0002        | 10.0  | 210  | 0.0195          | 10.3448 |
+
+
+### Framework versions
+
+- Transformers 4.40.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,65 @@
+{
+  "_name_or_path": "tarteel-ai/whisper-base-ar-quran",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "apply_spec_augment": false,
+  "architectures": [
+    "WhisperForConditionalGeneration"
+  ],
+  "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": [
+    [
+      1,
+      50272
+    ],
+    [
+      2,
+      50359
+    ],
+    [
+      3,
+      50363
+    ]
+  ],
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "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,
+  "suppress_tokens": [],
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.2",
+  "use_cache": false,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51865
+}

generation_config.json

@@ -0,0 +1,28 @@
+{
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "decoder_start_token_id": 50258,
+  "eos_token_id": 50257,
+  "forced_decoder_ids": [
+    [
+      1,
+      50272
+    ],
+    [
+      2,
+      50359
+    ],
+    [
+      3,
+      50363
+    ]
+  ],
+  "max_length": 1024,
+  "pad_token_id": 50257,
+  "suppress_tokens": [],
+  "transformers_version": "4.40.2",
+  "use_cache": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:543e65249aaf69cad9b483601aad8054c9745bf9c641bb048d768262a6315cd5
+size 290403936

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/May09_17-56-05_70784b0afc4f/events.out.tfevents.1715277375.70784b0afc4f.181.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5980ed7046c96328ded4939a99b810fa03a80a0c8b134a231dbdd3289598fba
+size 11190

runs/May09_18-26-37_70784b0afc4f/events.out.tfevents.1715279208.70784b0afc4f.181.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5611e373b43ac1adaf09bdd0b8c9d061ab70ea0efb2ffa949fb4aa70705af722
+size 11189

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e94aefd413b36fb79dca0053e1d1238e6a0465cbe829b18d4619073b0865662
+size 5112