End of training

README.md

@@ -19,13 +19,11 @@ model-index:
     dataset:
       name: Common Voice 11.0
       type: mozilla-foundation/common_voice_11_0
-      config: id
-      split: None
       args: 'config: id, split: test'
     metrics:
     - name: Wer
       type: wer
-      value: 59.896729776247845
+      value: 65.57659208261619
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -35,8 +33,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the Common Voice 11.0 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.4286
-- Wer: 59.8967
+- Loss: 1.0871
+- Wer: 65.5766
 
 ## Model description
 
@@ -55,35 +53,34 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 1e-05
+- learning_rate: 2e-05
 - train_batch_size: 32
 - 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
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 2
-- training_steps: 10
+- lr_scheduler_warmup_steps: 100
+- training_steps: 1000
 - mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Validation Loss | Wer     |
-|:-------------:|:------:|:----:|:---------------:|:-------:|
-| 1.7163        | 0.0159 | 1    | 1.8245          | 86.1446 |
-| 1.7097        | 0.0317 | 2    | 1.8245          | 86.1446 |
-| 1.7377        | 0.0476 | 3    | 1.8245          | 86.1446 |
-| 1.65          | 0.0635 | 4    | 1.8245          | 86.1446 |
-| 1.9103        | 0.0794 | 5    | 1.7649          | 68.5026 |
-| 1.7345        | 0.0952 | 6    | 1.6261          | 74.1824 |
-| 1.5202        | 0.1111 | 7    | 1.5249          | 59.6386 |
-| 1.5166        | 0.1270 | 8    | 1.4786          | 59.3804 |
-| 1.5636        | 0.1429 | 9    | 1.4523          | 59.5525 |
-| 1.5493        | 0.1587 | 10   | 1.4286          | 59.8967 |
+| Training Loss | Epoch   | Step | Validation Loss | Wer     |
+|:-------------:|:-------:|:----:|:---------------:|:-------:|
+| 1.1857        | 1.5873  | 100  | 0.9525          | 64.8881 |
+| 0.5773        | 3.1746  | 200  | 0.9205          | 59.1222 |
+| 0.2841        | 4.7619  | 300  | 0.9536          | 59.2943 |
+| 0.138         | 6.3492  | 400  | 0.9851          | 54.3890 |
+| 0.0694        | 7.9365  | 500  | 1.0057          | 59.6386 |
+| 0.0339        | 9.5238  | 600  | 1.0530          | 64.8021 |
+| 0.0195        | 11.1111 | 700  | 1.0620          | 61.1876 |
+| 0.013         | 12.6984 | 800  | 1.0752          | 57.1429 |
+| 0.0106        | 14.2857 | 900  | 1.0827          | 65.4045 |
+| 0.0097        | 15.8730 | 1000 | 1.0871          | 65.5766 |
 
 
 ### Framework versions
 
-- Transformers 4.46.3
+- Transformers 4.46.2
 - Pytorch 2.5.1+cu121
-- Datasets 3.1.0
 - Tokenizers 0.20.3

generation_config.json

@@ -236,5 +236,5 @@
     "transcribe": 50359,
     "translate": 50358
   },
-  "transformers_version": "4.46.3"
+  "transformers_version": "4.46.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2de22c9555d5490671a1f47959b8389242d4d86cdfe482107d9b6a1a5acb8166
+oid sha256:995ac42d2f09aeee8a88a9c2ea3793d24274e8b19430956bfa2c670f9db2bfc2
 size 151061672

runs/Nov25_04-10-27_d7d12cdf42f6/events.out.tfevents.1732507839.d7d12cdf42f6.1311.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed08bbb7359438ad07ccc5f332d83902628a032b58417a35358ee43a6b9d64a7
-size 11636
+oid sha256:b310aacbd0198ec3309d1da45d8469f757144b99ba11fc5e616f821c0e956ed5
+size 12519