End of training

README.md

@@ -1,44 +1,27 @@
 ---
 library_name: transformers
-language:
-- fr
 license: apache-2.0
 base_model: openai/whisper-tiny
 tags:
 - generated_from_trainer
-datasets:
-- mozilla-foundation/common_voice_11_0
 metrics:
 - wer
 model-index:
-- name: Whisper Tiny (Finetuned on French)
-  results:
-  - task:
-      name: Automatic Speech Recognition
-      type: automatic-speech-recognition
-    dataset:
-      name: Common Voice 11.0
-      type: mozilla-foundation/common_voice_11_0
-      config: fr
-      split: test
-      args: fr
-    metrics:
-    - name: Wer
-      type: wer
-      value: 0.4218038891187422
+- name: whisper-tiny-fr
+  results: []
 ---
 
 <!-- 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 Tiny (Finetuned on French)
+# whisper-tiny-fr
 
-This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the Common Voice 11.0 dataset.
+This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7793
-- Model Preparation Time: 0.0027
-- Wer: 0.4218
-- Cer: 0.1940
+- Loss: 0.6871
+- Model Preparation Time: 0.0056
+- Wer: 0.5022
+- Cer: 0.3447
 
 ## Model description
 
@@ -57,36 +40,40 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 1e-05
-- train_batch_size: 16
+- learning_rate: 0.0001
+- train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
-- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- training_steps: 12000
+- training_steps: 16000
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch  | Step  | Validation Loss | Model Preparation Time | Wer    | Cer    |
 |:-------------:|:------:|:-----:|:---------------:|:----------------------:|:------:|:------:|
-| 0.516         | 0.0833 | 1000  | 0.9995          | 0.0027                 | 0.4487 | 0.2213 |
-| 0.5283        | 0.1667 | 2000  | 0.9679          | 0.0027                 | 0.4511 | 0.2207 |
-| 0.5421        | 0.25   | 3000  | 0.9532          | 0.0027                 | 0.4462 | 0.2172 |
-| 0.5735        | 0.3333 | 4000  | 0.9474          | 0.0027                 | 0.4365 | 0.2110 |
-| 0.5774        | 0.4167 | 5000  | 0.9119          | 0.0027                 | 0.4794 | 0.2390 |
-| 0.591         | 0.5    | 6000  | 0.8834          | 0.0027                 | 0.4171 | 0.2024 |
-| 0.5218        | 0.5833 | 7000  | 0.8777          | 0.0027                 | 0.4293 | 0.2096 |
-| 0.4328        | 0.6667 | 8000  | 0.8750          | 0.0027                 | 0.4139 | 0.2017 |
-| 0.5392        | 0.75   | 9000  | 0.8736          | 0.0027                 | 0.5618 | 0.3050 |
-| 0.4311        | 0.8333 | 10000 | 0.8587          | 0.0027                 | 0.5618 | 0.3030 |
-| 0.4728        | 0.9167 | 11000 | 0.8514          | 0.0027                 | 0.4293 | 0.2034 |
-| 0.4521        | 1.0    | 12000 | 0.8516          | 0.0027                 | 0.4220 | 0.2054 |
+| 1.0566        | 0.0625 | 1000  | 1.3246          | 0.0056                 | 0.7494 | 0.4923 |
+| 0.8712        | 0.125  | 2000  | 1.1335          | 0.0056                 | 0.6508 | 0.4880 |
+| 0.7638        | 0.1875 | 3000  | 1.0380          | 0.0056                 | 0.5891 | 0.4386 |
+| 0.8262        | 0.25   | 4000  | 0.9789          | 0.0056                 | 0.5435 | 0.3623 |
+| 0.669         | 0.3125 | 5000  | 0.9403          | 0.0056                 | 0.5613 | 0.3955 |
+| 0.6105        | 0.375  | 6000  | 0.9065          | 0.0056                 | 0.5876 | 0.3812 |
+| 0.5432        | 0.4375 | 7000  | 0.8885          | 0.0056                 | 0.5350 | 0.3625 |
+| 0.5188        | 0.5    | 8000  | 0.8876          | 0.0056                 | 0.5612 | 0.3821 |
+| 0.6963        | 0.5625 | 9000  | 0.8451          | 0.0056                 | 0.5926 | 0.3922 |
+| 0.6387        | 0.625  | 10000 | 0.7571          | 0.0056                 | 0.4981 | 0.3410 |
+| 0.5572        | 0.6875 | 11000 | 0.7194          | 0.0056                 | 0.5045 | 0.3508 |
+| 0.5207        | 0.75   | 12000 | 0.7124          | 0.0056                 | 0.4742 | 0.3312 |
+| 0.4515        | 0.8125 | 13000 | 0.7004          | 0.0056                 | 0.4817 | 0.3345 |
+| 0.4858        | 0.875  | 14000 | 0.7089          | 0.0056                 | 0.4602 | 0.3271 |
+| 0.4601        | 0.9375 | 15000 | 0.6796          | 0.0056                 | 0.5509 | 0.3672 |
+| 0.4808        | 1.0    | 16000 | 0.6719          | 0.0056                 | 0.4443 | 0.2966 |
 
 
 ### Framework versions
 
-- Transformers 4.46.3
-- Pytorch 2.5.1+cu121
-- Datasets 3.1.0
-- Tokenizers 0.20.3
+- Transformers 4.49.0
+- Pytorch 2.6.0+cu124
+- Datasets 3.4.1
+- Tokenizers 0.21.1

config.json

@@ -54,7 +54,7 @@
   "pad_token_id": 50257,
   "scale_embedding": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.46.3",
+  "transformers_version": "4.49.0",
   "use_cache": true,
   "use_weighted_layer_sum": false,
   "vocab_size": 51865

generation_config.json

@@ -236,5 +236,5 @@
     "transcribe": 50359,
     "translate": 50358
   },
-  "transformers_version": "4.46.3"
+  "transformers_version": "4.49.0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5bedfa33ed7973b7eec6cb1db0e4306013e0a76cf157ac259b1ecd0fc7bb48b
+oid sha256:9cefe71e77c49e46e78f5e38f5f1fc250a329f0f46766a4a751dd90496e7ef52
 size 151061672

runs/Mar17_21-30-31_b2a92614898a/events.out.tfevents.1742247247.b2a92614898a.765.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67c09115fa4b6193bf257a8cb20efbbf9d3500c4b75548391f6e25a4e19633ed
+size 17590

runs/Mar17_22-01-24_b2a92614898a/events.out.tfevents.1742249066.b2a92614898a.8333.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b38013ae3a641fc46e0dd0ce3918774da8a16503b63b2a96b9092311ef6a0301
+size 149743

runs/Mar17_22-01-24_b2a92614898a/events.out.tfevents.1742260399.b2a92614898a.8333.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f77f7e494b3128425dd5223ca1df3b20d1325c7d792d5fc299dab6655a310e79
+size 519

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45658c1cc60c2da0b7d59182fce10b2b6e19016fc491eacdf8458053c2178f63
-size 5432
+oid sha256:82dc1bd201f593001f8f33ed0e96717f04f96861409b704e895d5861edaeefb4
+size 5560