End of training

README.md

@@ -1,6 +1,4 @@
 ---
-language:
-- zh
 license: apache-2.0
 base_model: openai/whisper-tiny
 tags:
@@ -19,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the Hanhpt23/ChineseMed dataset.
 It achieves the following results on the evaluation set:
-- Loss: 5.4554
-- Wer: 132.7991
+- Loss: 4.7716
+- Wer: 115.5556
 
 ## Model description
 
@@ -50,28 +48,28 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step  | Validation Loss | Wer      |
-|:-------------:|:-----:|:-----:|:---------------:|:--------:|
-| 3.0558        | 1.0   | 2222  | 3.0833          | 127.4184 |
-| 2.5492        | 2.0   | 4444  | 3.0648          | 130.1088 |
-| 2.0618        | 3.0   | 6666  | 3.2779          | 112.4785 |
-| 1.5376        | 4.0   | 8888  | 3.6124          | 132.1122 |
-| 1.1944        | 5.0   | 11110 | 3.9546          | 112.3641 |
-| 0.8561        | 6.0   | 13332 | 4.3130          | 125.9874 |
-| 0.6536        | 7.0   | 15554 | 4.5104          | 138.4659 |
-| 0.4346        | 8.0   | 17776 | 4.7482          | 113.7378 |
-| 0.411         | 9.0   | 19998 | 4.9091          | 134.0584 |
-| 0.3214        | 10.0  | 22220 | 4.9981          | 124.9571 |
-| 0.3408        | 11.0  | 24442 | 5.0642          | 137.0922 |
-| 0.2991        | 12.0  | 26664 | 5.1118          | 116.9433 |
-| 0.3083        | 13.0  | 28886 | 5.2996          | 132.7418 |
-| 0.2714        | 14.0  | 31108 | 5.3376          | 115.1116 |
-| 0.3389        | 15.0  | 33330 | 5.3140          | 125.2433 |
-| 0.2698        | 16.0  | 35552 | 5.3652          | 116.7716 |
-| 0.2698        | 17.0  | 37774 | 5.3976          | 118.8323 |
-| 0.2836        | 18.0  | 39996 | 5.4280          | 123.9267 |
-| 0.2192        | 19.0  | 42218 | 5.4235          | 131.3108 |
-| 0.2257        | 20.0  | 44440 | 5.4554          | 132.7991 |
+| Training Loss | Epoch | Step | Validation Loss | Wer      |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 2.2347        | 1.0   | 371  | 3.0537          | 111.1111 |
+| 1.7551        | 2.0   | 742  | 3.0133          | 105.5556 |
+| 1.3384        | 3.0   | 1113 | 3.2446          | 107.7778 |
+| 0.7899        | 4.0   | 1484 | 3.5971          | 112.2222 |
+| 0.424         | 5.0   | 1855 | 3.8711          | 117.7778 |
+| 0.179         | 6.0   | 2226 | 4.0705          | 137.7778 |
+| 0.0953        | 7.0   | 2597 | 4.2723          | 112.2222 |
+| 0.0628        | 8.0   | 2968 | 4.4901          | 116.6667 |
+| 0.0386        | 9.0   | 3339 | 4.3978          | 113.3333 |
+| 0.0299        | 10.0  | 3710 | 4.5975          | 113.3333 |
+| 0.0198        | 11.0  | 4081 | 4.6376          | 108.8889 |
+| 0.0074        | 12.0  | 4452 | 4.6874          | 112.2222 |
+| 0.0046        | 13.0  | 4823 | 4.6807          | 110.0000 |
+| 0.0006        | 14.0  | 5194 | 4.7271          | 117.7778 |
+| 0.0052        | 15.0  | 5565 | 4.7211          | 111.1111 |
+| 0.0017        | 16.0  | 5936 | 4.7438          | 112.2222 |
+| 0.0003        | 17.0  | 6307 | 4.7391          | 120.0    |
+| 0.0002        | 18.0  | 6678 | 4.7585          | 120.0    |
+| 0.0002        | 19.0  | 7049 | 4.7621          | 114.4444 |
+| 0.0002        | 20.0  | 7420 | 4.7716          | 115.5556 |
 
 
 ### Framework versions

generation_config.json

@@ -144,6 +144,7 @@
     "<|yo|>": 50325,
     "<|zh|>": 50260
   },
+  "language": null,
   "max_initial_timestamp_index": 50,
   "max_length": 448,
   "no_timestamps_token_id": 50363,
@@ -240,6 +241,7 @@
     50361,
     50362
   ],
+  "task": "transcribe",
   "task_to_id": {
     "transcribe": 50359,
     "translate": 50358

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4121df3226c1a67ec12fb6806cf407fac5b1902b96c4da6fd3e8d92b8625d8fe
+oid sha256:9d7a583d9c516a222d8d86be63eac0be7217d353a3a1fce48c366b300e250faf
 size 151061672