End of training

README.md

@@ -5,7 +5,7 @@ tags:
 - generated_from_trainer
 datasets:
 - common_voice_13_0
-base_model: openai/whisper-large-v2
+base_model: openai/whisper-tiny
 model-index:
 - name: arabic_speech_ASR_Whisper
   results: []
@@ -16,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # arabic_speech_ASR_Whisper
 
-This model is a fine-tuned version of [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2) on the common_voice_13_0 dataset.
+This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the common_voice_13_0 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3188
+- Loss: 0.4170
 
 ## Model description
 
@@ -43,22 +43,17 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 10
+- num_epochs: 5
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.2742        | 1.0   | 134  | 0.3322          |
-| 0.155         | 2.0   | 268  | 0.3044          |
-| 0.1179        | 3.0   | 402  | 0.3179          |
-| 0.0498        | 4.0   | 536  | 0.2988          |
-| 0.0334        | 5.0   | 670  | 0.2914          |
-| 0.0184        | 6.0   | 804  | 0.2996          |
-| 0.007         | 7.0   | 938  | 0.3169          |
-| 0.0095        | 8.0   | 1072 | 0.3081          |
-| 0.0024        | 9.0   | 1206 | 0.3148          |
-| 0.0022        | 10.0  | 1340 | 0.3188          |
+| 0.6558        | 1.0   | 1334 | 0.6054          |
+| 0.4922        | 2.0   | 2668 | 0.5290          |
+| 0.4324        | 3.0   | 4002 | 0.4767          |
+| 0.3572        | 4.0   | 5336 | 0.4277          |
+| 0.2179        | 5.0   | 6670 | 0.4170          |
 
 
 ### Framework versions

adapter_config.json

@@ -4,7 +4,7 @@
     "base_model_class": "WhisperForConditionalGeneration",
     "parent_library": "transformers.models.whisper.modeling_whisper"
   },
-  "base_model_name_or_path": "openai/whisper-large-v2",
+  "base_model_name_or_path": "openai/whisper-tiny",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -22,8 +22,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj"
+    "v_proj",
+    "q_proj"
   ],
   "task_type": null,
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:357437fee1b034f93c9b03f2e04d442536d8ed18754c83b655a3f015601e2f1f
-size 62969640
+oid sha256:0b605d1928cd82cf8ac8adfdd154bc5d15f19c42fc171f1f8eb1d0e142db67aa
+size 2366008

runs/Mar06_12-01-53_4f68f4e4580e/events.out.tfevents.1709726515.4f68f4e4580e.282.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:081bc9410336e87d127efbb725b9574b8c9b26b18664f35d091a736214137d60
+size 64669

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb7410fe1e84721749072135e285a4cfae931c9a89dd82b3b25e3141521fa101
+oid sha256:526cc3d10035f29e3b27a718cfe222a35736e370ab8ba42242a8ef8083da20f5
 size 5112