End of training

README.md

@@ -2,9 +2,9 @@
 language:
 - ru
 license: apache-2.0
+base_model: openai/whisper-tiny
 tags:
 - generated_from_trainer
-base_model: openai/whisper-tiny
 datasets:
 - bond005/podlodka_speech
 metrics:
@@ -13,16 +13,16 @@ model-index:
 - name: whisper-tiny-ru
   results:
   - task:
-      type: automatic-speech-recognition
       name: Automatic Speech Recognition
+      type: automatic-speech-recognition
     dataset:
       name: Podlodka Speech
       type: bond005/podlodka_speech
       args: 'config: ru, split: test'
     metrics:
-    - type: wer
-      value: 96.58792650918635
-      name: Wer
+    - name: Wer
+      type: wer
+      value: 87.57655293088365
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ 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 Podlodka Speech dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.2475
-- Wer: 96.5879
+- Loss: 1.2560
+- Wer: 87.5766
 
 ## Model description
 
@@ -58,18 +58,18 @@ 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
-- lr_scheduler_warmup_steps: 40
+- lr_scheduler_warmup_steps: 200
 - training_steps: 200
 
 ### Training results
 
-| Training Loss | Epoch   | Step | Validation Loss | Wer      |
-|:-------------:|:-------:|:----:|:---------------:|:--------:|
-| 0.9999        | 4.4444  | 40   | 1.2054          | 71.8285  |
-| 0.4535        | 8.8889  | 80   | 1.1539          | 73.2283  |
-| 0.2849        | 13.3333 | 120  | 1.1958          | 104.5494 |
-| 0.1674        | 17.7778 | 160  | 1.2339          | 79.0901  |
-| 0.1372        | 22.2222 | 200  | 1.2475          | 96.5879  |
+| Training Loss | Epoch   | Step | Validation Loss | Wer     |
+|:-------------:|:-------:|:----:|:---------------:|:-------:|
+| 1.1866        | 4.4444  | 40   | 1.2435          | 56.4304 |
+| 0.9133        | 8.8889  | 80   | 1.2109          | 68.6789 |
+| 0.6381        | 13.3333 | 120  | 1.1414          | 77.2528 |
+| 0.3374        | 17.7778 | 160  | 1.1691          | 83.2021 |
+| 0.175         | 22.2222 | 200  | 1.2560          | 87.5766 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:065b5627332cfb0525dedf674372ef415d14389326aa0dccc0a7e8908273709d
+oid sha256:15b8ab4b0b464acdece550f76b6bf11190acca1e8fec7548408eab2bcc3747d2
 size 151061672