Model save

README.md

@@ -17,8 +17,8 @@ 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: 2.2916
-- Wer: 93.6170
+- Loss: 2.2824
+- Wer: 23.4043
 
 ## Model description
 
@@ -51,10 +51,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss | Wer     |
 |:-------------:|:------:|:----:|:---------------:|:-------:|
-| 0.0           | 1000.0 | 1000 | 1.2180          | 70.2128 |
-| 0.0           | 2000.0 | 2000 | 1.8218          | 89.3617 |
-| 0.0           | 3000.0 | 3000 | 2.1168          | 91.4894 |
-| 0.0           | 4000.0 | 4000 | 2.2916          | 93.6170 |
+| 0.0           | 1000.0 | 1000 | 1.2190          | 21.2766 |
+| 0.0           | 2000.0 | 2000 | 1.8245          | 21.2766 |
+| 0.0           | 3000.0 | 3000 | 2.1077          | 23.4043 |
+| 0.0           | 4000.0 | 4000 | 2.2824          | 23.4043 |
 
 
 ### Framework versions

generation_config.json

@@ -150,6 +150,7 @@
     "<|yo|>": 50325,
     "<|zh|>": 50260
   },
+  "language": "spanish",
   "max_initial_timestamp_index": 50,
   "max_length": 448,
   "no_timestamps_token_id": 50363,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f222c6e53341b22a0a96e8681e6679ce1018e36cf036a9b566da359e8bf4b8d
+oid sha256:ad1c19bc0704d1015180c96fa752f0625d5c0774fea25131773fa44d21188972
 size 966995080