End of training

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-base](https://huggingface.co/openai/whisper-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0113
-- Wer: 74.0448
+- Loss: 0.0364
+- Wer: 26.1302
 
 ## Model description
 
@@ -51,10 +51,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss | Wer     |
 |:-------------:|:------:|:----:|:---------------:|:-------:|
-| 0.0173        | 0.3671 | 500  | 0.0139          | 70.8788 |
-| 0.0194        | 0.7342 | 1000 | 0.0130          | 48.4443 |
-| 0.0172        | 1.1013 | 1500 | 0.0119          | 56.8231 |
-| 0.0117        | 1.4684 | 2000 | 0.0113          | 74.0448 |
+| 0.5133        | 0.3671 | 500  | 0.0835          | 50.8073 |
+| 0.0607        | 0.7342 | 1000 | 0.0469          | 32.2390 |
+| 0.0431        | 1.1013 | 1500 | 0.0398          | 27.9064 |
+| 0.0339        | 1.4684 | 2000 | 0.0364          | 26.1302 |
 
 
 ### Framework versions

generation_config.json

@@ -1,4 +1,38 @@
 {
+  "alignment_heads": [
+    [
+      3,
+      1
+    ],
+    [
+      4,
+      2
+    ],
+    [
+      4,
+      3
+    ],
+    [
+      4,
+      7
+    ],
+    [
+      5,
+      1
+    ],
+    [
+      5,
+      2
+    ],
+    [
+      5,
+      4
+    ],
+    [
+      5,
+      6
+    ]
+  ],
   "begin_suppress_tokens": [
     220,
     50257
@@ -9,19 +43,121 @@
   "forced_decoder_ids": [
     [
       1,
-      50259
+      null
     ],
     [
       2,
       50359
-    ],
-    [
-      3,
-      50363
     ]
   ],
+  "is_multilingual": true,
+  "lang_to_id": {
+    "<|af|>": 50327,
+    "<|am|>": 50334,
+    "<|ar|>": 50272,
+    "<|as|>": 50350,
+    "<|az|>": 50304,
+    "<|ba|>": 50355,
+    "<|be|>": 50330,
+    "<|bg|>": 50292,
+    "<|bn|>": 50302,
+    "<|bo|>": 50347,
+    "<|br|>": 50309,
+    "<|bs|>": 50315,
+    "<|ca|>": 50270,
+    "<|cs|>": 50283,
+    "<|cy|>": 50297,
+    "<|da|>": 50285,
+    "<|de|>": 50261,
+    "<|el|>": 50281,
+    "<|en|>": 50259,
+    "<|es|>": 50262,
+    "<|et|>": 50307,
+    "<|eu|>": 50310,
+    "<|fa|>": 50300,
+    "<|fi|>": 50277,
+    "<|fo|>": 50338,
+    "<|fr|>": 50265,
+    "<|gl|>": 50319,
+    "<|gu|>": 50333,
+    "<|haw|>": 50352,
+    "<|ha|>": 50354,
+    "<|he|>": 50279,
+    "<|hi|>": 50276,
+    "<|hr|>": 50291,
+    "<|ht|>": 50339,
+    "<|hu|>": 50286,
+    "<|hy|>": 50312,
+    "<|id|>": 50275,
+    "<|is|>": 50311,
+    "<|it|>": 50274,
+    "<|ja|>": 50266,
+    "<|jw|>": 50356,
+    "<|ka|>": 50329,
+    "<|kk|>": 50316,
+    "<|km|>": 50323,
+    "<|kn|>": 50306,
+    "<|ko|>": 50264,
+    "<|la|>": 50294,
+    "<|lb|>": 50345,
+    "<|ln|>": 50353,
+    "<|lo|>": 50336,
+    "<|lt|>": 50293,
+    "<|lv|>": 50301,
+    "<|mg|>": 50349,
+    "<|mi|>": 50295,
+    "<|mk|>": 50308,
+    "<|ml|>": 50296,
+    "<|mn|>": 50314,
+    "<|mr|>": 50320,
+    "<|ms|>": 50282,
+    "<|mt|>": 50343,
+    "<|my|>": 50346,
+    "<|ne|>": 50313,
+    "<|nl|>": 50271,
+    "<|nn|>": 50342,
+    "<|no|>": 50288,
+    "<|oc|>": 50328,
+    "<|pa|>": 50321,
+    "<|pl|>": 50269,
+    "<|ps|>": 50340,
+    "<|pt|>": 50267,
+    "<|ro|>": 50284,
+    "<|ru|>": 50263,
+    "<|sa|>": 50344,
+    "<|sd|>": 50332,
+    "<|si|>": 50322,
+    "<|sk|>": 50298,
+    "<|sl|>": 50305,
+    "<|sn|>": 50324,
+    "<|so|>": 50326,
+    "<|sq|>": 50317,
+    "<|sr|>": 50303,
+    "<|su|>": 50357,
+    "<|sv|>": 50273,
+    "<|sw|>": 50318,
+    "<|ta|>": 50287,
+    "<|te|>": 50299,
+    "<|tg|>": 50331,
+    "<|th|>": 50289,
+    "<|tk|>": 50341,
+    "<|tl|>": 50348,
+    "<|tr|>": 50268,
+    "<|tt|>": 50351,
+    "<|uk|>": 50280,
+    "<|ur|>": 50290,
+    "<|uz|>": 50337,
+    "<|vi|>": 50278,
+    "<|yi|>": 50335,
+    "<|yo|>": 50325,
+    "<|zh|>": 50260
+  },
+  "max_initial_timestamp_index": 50,
   "max_length": 448,
+  "no_timestamps_token_id": 50363,
   "pad_token_id": 50257,
+  "prev_sot_token_id": 50361,
+  "return_timestamps": false,
   "suppress_tokens": [
     1,
     2,
@@ -112,6 +248,9 @@
     50361,
     50362
   ],
-  "transformers_version": "4.41.2",
-  "use_cache": false
+  "task_to_id": {
+    "transcribe": 50359,
+    "translate": 50358
+  },
+  "transformers_version": "4.41.2"
 }