End of training

README.md

@@ -1,59 +1,53 @@
 ---
+language:
+- ar
 license: apache-2.0
 base_model: openai/whisper-small
 tags:
-- audio
-- automatic-speech-recognition
+- generated_from_trainer
 datasets:
 - mozilla-foundation/common_voice_16_1
 metrics:
 - wer
-widget:
-  - example_title: Sample 1
-    src: sample_ar.mp3
 model-index:
-- name: whisper-small-ar-v1
+- name: Whisper Small AR v.2
   results:
   - task:
       name: Automatic Speech Recognition
       type: automatic-speech-recognition
     dataset:
-      name: mozilla-foundation/common_voice_16_1
+      name: Common Voice 16.1
       type: mozilla-foundation/common_voice_16_1
       config: ar
       split: test
-      args: ar
+      args: 'config: ar, split: test'
     metrics:
     - name: Wer
       type: wer
-      value: 158.15321276282899
-language:
-- ar
-library_name: transformers
-pipeline_tag: automatic-speech-recognition
+      value: 47.726437288634024
 ---
 
+<!-- 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 v.2
 
-# whisper-small-ar-v1
-
-This model is for Arabic automatic speech recognition (ASR). It is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Arabic portion of the `mozilla-foundation/common_voice_16_1` dataset.
+This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 16.1 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3354
-- Wer: 158.1532
+- Loss: 0.4007
+- Wer: 47.7264
 
 ## Model description
 
-Whisper model fine-tuned on Arabic data, following the [official tutorial](https://huggingface.co/blog/fine-tune-whisper).
+More information needed
 
 ## Intended uses & limitations
 
-The model is not fully trained yet. Hence, it is not intended for professional use.
+More information needed
 
 ## Training and evaluation data
 
-Training Data: CommonVoice (v16.1) Arabic train + validation splits  
-Validation Data: CommonVoice (v16.1) Arabic test split
+More information needed
 
 ## Training procedure
 
@@ -62,12 +56,12 @@ Validation Data: CommonVoice (v16.1) Arabic test split
 The following hyperparameters were used during training:
 - learning_rate: 1e-05
 - train_batch_size: 32
-- eval_batch_size: 8
+- eval_batch_size: 32
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 500
-- training_steps: 4000
+- training_steps: 8000
 - mixed_precision_training: Native AMP
 
 ### Training results
@@ -78,11 +72,15 @@ The following hyperparameters were used during training:
 | 0.1625        | 1.65  | 2000 | 0.3353          | 228.5252 |
 | 0.1002        | 2.47  | 3000 | 0.3311          | 238.8858 |
 | 0.0751        | 3.3   | 4000 | 0.3354          | 158.1532 |
+| 0.0601        | 4.12  | 5000 | 0.3576          | 48.9285  |
+| 0.0612        | 4.95  | 6000 | 0.3575          | 47.8937  |
+| 0.0383        | 5.77  | 7000 | 0.3819          | 46.9085  |
+| 0.0234        | 6.6   | 8000 | 0.4007          | 47.7264  |
 
 
 ### Framework versions
 
-- Transformers 4.37.2
-- Pytorch 2.2.0+cu121
-- Datasets 2.17.0
-- Tokenizers 0.15.2
+- Transformers 4.38.1
+- Pytorch 2.1.0+cu118
+- Datasets 2.17.1
+- Tokenizers 0.15.2

generation_config.json

@@ -160,6 +160,7 @@
     "<|yo|>": 50325,
     "<|zh|>": 50260
   },
+  "language": "ar",
   "max_initial_timestamp_index": 50,
   "max_length": 448,
   "no_timestamps_token_id": 50363,
@@ -260,5 +261,5 @@
     "transcribe": 50359,
     "translate": 50358
   },
-  "transformers_version": "4.37.2"
+  "transformers_version": "4.38.1"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13e7facde86539541c80f11c64091cade393267417e5cf8f826c3642ab773d18
+oid sha256:a639b02ee64c35036e7ca0ddde2f68f6038de017a5d43a8615dd227728d62c8c
 size 966995080

runs/Feb24_23-41-48_326117fcf43d/events.out.tfevents.1708818121.326117fcf43d.12625.5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9a241436d2024cfc3e93dc4df607621ce5d56f4085e26eeb59cf73ae59e15f7
-size 40459
+oid sha256:560384fcfe65e7ff79a437f63579428891cb0eb6eefc30b18ac5a1e7263d6196
+size 40813