End of training

README.md

@@ -33,7 +33,7 @@ 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 arrow dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7401
+- Loss: 0.7659
 - Wer: 16.8539
 
 ## Model description
@@ -69,15 +69,15 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Wer     |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|
-| 0.5273        | 10.0  | 50   | 1.0422          | 15.7303 |
-| 0.1704        | 20.0  | 100  | 0.7306          | 16.8539 |
-| 0.0004        | 30.0  | 150  | 0.7250          | 15.7303 |
-| 0.0003        | 40.0  | 200  | 0.7401          | 16.8539 |
+| 0.515         | 10.0  | 50   | 1.0232          | 16.8539 |
+| 0.1717        | 20.0  | 100  | 0.7364          | 19.1011 |
+| 0.0006        | 30.0  | 150  | 0.7300          | 15.7303 |
+| 0.0003        | 40.0  | 200  | 0.7659          | 16.8539 |
 
 
 ### Framework versions
 
-- Transformers 4.38.0.dev0
-- Pytorch 2.0.0
+- Transformers 4.42.0.dev0
+- Pytorch 2.2.0+cu121
 - Datasets 2.16.1
-- Tokenizers 0.15.0
+- Tokenizers 0.19.1

generation_config.json

@@ -160,10 +160,11 @@
     "<|yo|>": 50325,
     "<|zh|>": 50260
   },
-  "max_initial_timestamp_index": 1,
+  "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,
@@ -259,5 +260,5 @@
     "transcribe": 50359,
     "translate": 50358
   },
-  "transformers_version": "4.38.0.dev0"
+  "transformers_version": "4.42.0.dev0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c90d89367ec1e5d50691b4b7227b1910b57f83692258a0bb27e63a91106f61ad
+oid sha256:00d6601a39fd58cb5cb12e4409823a1f3be497ce6597842d50dbfb2be75bd858
 size 966995080