End of training

README.md

@@ -25,7 +25,7 @@ model-index:
     metrics:
     - name: Wer
       type: wer
-      value: 65.68187589943282
+      value: 60.3403030559553
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -35,8 +35,8 @@ 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 Common Voice 11.0 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5952
-- Wer: 65.6819
+- Loss: 0.5276
+- Wer: 60.3403
 
 ## Model description
 
@@ -62,19 +62,19 @@ The following hyperparameters were used during training:
 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 10
-- training_steps: 1000
+- training_steps: 2500
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss | Wer     |
 |:-------------:|:------:|:----:|:---------------:|:-------:|
-| 0.4581        | 0.6116 | 1000 | 0.5952          | 65.6819 |
+| 0.2838        | 1.5291 | 2500 | 0.5276          | 60.3403 |
 
 
 ### Framework versions
 
-- Transformers 4.52.4
+- Transformers 4.53.0
 - Pytorch 2.6.0+cu124
 - Datasets 3.6.0
 - Tokenizers 0.21.1

config.json

@@ -53,7 +53,7 @@
   "pad_token_id": 50257,
   "scale_embedding": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.52.4",
+  "transformers_version": "4.53.0",
   "use_cache": true,
   "use_weighted_layer_sum": false,
   "vocab_size": 51865

generation_config.json

@@ -32,6 +32,7 @@
   "bos_token_id": 50257,
   "decoder_start_token_id": 50258,
   "eos_token_id": 50257,
+  "forced_decoder_ids": null,
   "is_multilingual": true,
   "lang_to_id": {
     "<|af|>": 50327,
@@ -236,5 +237,5 @@
     "transcribe": 50359,
     "translate": 50358
   },
-  "transformers_version": "4.52.4"
+  "transformers_version": "4.53.0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb8e5897d6d417052a95e84533809ba6db80d202c66989ed088f81f5a1a80fe6
+oid sha256:776b10cbca05186bd0342a69e3ff798f91c7a4d4e772c1355a4bc99b2772b95b
 size 151061672

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75ecc9444717f31462875799b6c57200b37954424e867524dad52ba74a9219c0
-size 5432
+oid sha256:53a25a964b6ad90c80964e49ef7af460360b38b823d49400ebb1732f94e4186f
+size 5496