Model save

README.md

@@ -16,10 +16,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # whisper-large-v3-ft-btb-ca-cy
 
-This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on the DewiBrynJones/banc-trawsgrifiadau-bangor-clean train main, cymen-arfor/15awr train+dev main dataset.
+This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4080
-- Wer: 0.2782
+- Loss: 0.3810
+- Wer: 0.2750
 
 ## Model description
 
@@ -54,16 +54,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss | Wer    |
 |:-------------:|:------:|:----:|:---------------:|:------:|
-| 0.9864        | 0.6555 | 1000 | 0.4853          | 0.3736 |
-| 0.6533        | 1.3110 | 2000 | 0.4187          | 0.3088 |
-| 0.5981        | 1.9666 | 3000 | 0.3845          | 0.2868 |
-| 0.3903        | 2.6221 | 4000 | 0.3909          | 0.2854 |
-| 0.2479        | 3.2776 | 5000 | 0.4080          | 0.2782 |
+| 0.5152        | 0.5411 | 1000 | 0.4954          | 0.3535 |
+| 0.3339        | 1.0823 | 2000 | 0.4205          | 0.3198 |
+| 0.3189        | 1.6234 | 3000 | 0.3911          | 0.2913 |
+| 0.2051        | 2.1645 | 4000 | 0.3863          | 0.2790 |
+| 0.202         | 2.7056 | 5000 | 0.3810          | 0.2750 |
 
 
 ### Framework versions
 
-- Transformers 4.46.1
+- Transformers 4.46.2
 - Pytorch 2.5.1+cu124
 - Datasets 3.1.0
-- Tokenizers 0.20.1
+- Tokenizers 0.20.3

generation_config.json

@@ -151,7 +151,7 @@
     "<|yue|>": 50358,
     "<|zh|>": 50260
   },
-  "language": "welsh",
+  "language": null,
   "max_initial_timestamp_index": 50,
   "max_length": 448,
   "no_timestamps_token_id": 50364,
@@ -253,5 +253,5 @@
     "transcribe": 50360,
     "translate": 50359
   },
-  "transformers_version": "4.46.1"
+  "transformers_version": "4.46.2"
 }