Model save

README.md

@@ -1,16 +1,13 @@
 ---
+license: apache-2.0
+base_model: openai/whisper-tiny
 tags:
 - generated_from_trainer
 metrics:
 - wer
 model-index:
-- name: whisper-tiny-ft-cy
+- name: whisper-tiny-ft-cy-en
   results: []
-license: apache-2.0
-language:
-- cy
-- en
-pipeline_tag: automatic-speech-recognition
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -18,21 +15,22 @@ should probably proofread and complete it, then remove this comment. -->
 
 # whisper-tiny-ft-cy-en
 
-This model is a fine-tune of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) using custom splits from 
-Common Voice 16.1 Welsh and English datasets as well as normalized verbatim transcriptions from 
-[techiaith/banc-trawsgrifiadau-bangor](https://huggingface.co/datasets/techiaith/banc-trawsgrifiadau-bangor)
+This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5668
+- Wer: 36.8865
+
+## Model description
+
+More information needed
 
 ## Intended uses & limitations
 
-Due to its small size, this model is intended to be used as the basis for offline speech recognition on devices such as 
-Android phones. 
+More information needed
 
 ## Training and evaluation data
 
-It achieves the following results on the evaluation set:
-
-- Loss: 0.7176
-- Wer: 53.1135
+More information needed
 
 ## Training procedure
 
@@ -41,28 +39,27 @@ It achieves the following results on the evaluation set:
 The following hyperparameters were used during training:
 - learning_rate: 1e-05
 - train_batch_size: 4
-- eval_batch_size: 8
+- eval_batch_size: 1
 - seed: 42
 - gradient_accumulation_steps: 8
 - total_train_batch_size: 32
 - 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: 3000
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Wer     |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|
-| 0.8115        | 1.41  | 1000 | 0.8426          | 60.0795 |
-| 0.6396        | 2.83  | 2000 | 0.7508          | 54.4259 |
-| 0.5259        | 4.24  | 3000 | 0.7255          | 53.1328 |
-| 0.4854        | 5.66  | 4000 | 0.7176          | 53.1135 |
+| 0.7039        | 0.25  | 1000 | 0.6932          | 43.4217 |
+| 0.5689        | 0.5   | 2000 | 0.5930          | 38.4145 |
+| 0.5255        | 0.75  | 3000 | 0.5668          | 36.8865 |
 
 
 ### Framework versions
 
-- Transformers 4.37.2
-- Pytorch 2.2.0+cu121
-- Datasets 2.16.1
-- Tokenizers 0.15.1
+- Transformers 4.39.3
+- Pytorch 2.2.2+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

generation_config.json

@@ -244,5 +244,5 @@
     "transcribe": 50359,
     "translate": 50358
   },
-  "transformers_version": "4.37.2"
+  "transformers_version": "4.39.3"
 }