End of training

README.md

@@ -20,8 +20,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.1695
-- Wer: 34.5756
+- Loss: 0.4981
+- Wer: 23.7740
 
 ## Model description
 
@@ -54,10 +54,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Wer     |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|
-| 0.0041        | 62.5  | 250  | 1.1011          | 63.9752 |
-| 0.0005        | 125.0 | 500  | 1.1408          | 49.8965 |
-| 0.0002        | 187.5 | 750  | 1.1630          | 38.3023 |
-| 0.0002        | 250.0 | 1000 | 1.1695          | 34.5756 |
+| 0.0584        | 25.0  | 250  | 0.4929          | 26.6525 |
+| 0.0046        | 50.0  | 500  | 0.4742          | 24.3070 |
+| 0.0005        | 75.0  | 750  | 0.4932          | 21.7484 |
+| 0.0004        | 100.0 | 1000 | 0.4981          | 23.7740 |
 
 
 ### Framework versions

generation_config.json

@@ -150,7 +150,7 @@
     "<|yo|>": 50325,
     "<|zh|>": 50260
   },
-  "language": "Spanish",
+  "language": "spanish",
   "max_initial_timestamp_index": 50,
   "max_length": 600,
   "no_timestamps_token_id": 50363,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ced72af41605fdf989ba63fbd9ec69aed133444e79915857744c505f3f19039
+oid sha256:a91cfb4361362ecd10d0bdd33df9fab2d28c6f8bee5fed699e3e639eeb26c386
 size 966995080