End of training

README.md

@@ -2,8 +2,7 @@
 library_name: peft
 language:
 - it
-license: apache-2.0
-base_model: openai/whisper-medium
+base_model: b-brave/asr_double_training_15-10-2024_merged
 tags:
 - generated_from_trainer
 datasets:
@@ -24,7 +23,7 @@ model-index:
       args: default
     metrics:
     - type: wer
-      value: 99.25650557620817
+      value: 35.93556381660471
       name: Wer
 ---
 
@@ -33,10 +32,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Whisper Medium
 
-This model is a fine-tuned version of [b-brave/asr_double_training_15-10-2024](https://huggingface.co/b-brave/asr_double_training_15-10-2024) on the ASR_BB_and_EC dataset.
+This model is a fine-tuned version of [b-brave/asr_double_training_15-10-2024_merged](https://huggingface.co/b-brave/asr_double_training_15-10-2024_merged) on the ASR_BB_and_EC dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3558
-- Wer: 99.2565
+- Loss: 0.4742
+- Wer: 35.9356
 
 ## Model description
 
@@ -55,7 +54,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.001
+- learning_rate: 1e-06
 - train_batch_size: 16
 - eval_batch_size: 16
 - seed: 42
@@ -69,14 +68,14 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Validation Loss | Wer      |
-|:-------------:|:------:|:----:|:---------------:|:--------:|
-| 1.45          | 0.8929 | 100  | 0.5234          | 276.4560 |
-| 0.4134        | 1.7857 | 200  | 0.3877          | 96.9021  |
-| 0.2336        | 2.6786 | 300  | 0.3877          | 44.4857  |
-| 0.1324        | 3.5714 | 400  | 0.3650          | 45.6010  |
-| 0.085         | 4.4643 | 500  | 0.3540          | 39.4052  |
-| 0.0643        | 5.3571 | 600  | 0.3558          | 99.2565  |
+| Training Loss | Epoch  | Step | Validation Loss | Wer     |
+|:-------------:|:------:|:----:|:---------------:|:-------:|
+| 0.7705        | 0.8929 | 100  | 0.4884          | 36.5551 |
+| 0.7194        | 1.7857 | 200  | 0.4838          | 36.6791 |
+| 0.7372        | 2.6786 | 300  | 0.4806          | 36.4312 |
+| 0.6967        | 3.5714 | 400  | 0.4782          | 36.3073 |
+| 0.649         | 4.4643 | 500  | 0.4761          | 36.3073 |
+| 0.7127        | 5.3571 | 600  | 0.4742          | 35.9356 |
 
 
 ### Framework versions

adapter_config.json

@@ -4,7 +4,7 @@
     "base_model_class": "WhisperForConditionalGeneration",
     "parent_library": "transformers.models.whisper.modeling_whisper"
   },
-  "base_model_name_or_path": "openai/whisper-medium",
+  "base_model_name_or_path": "b-brave/asr_double_training_15-10-2024_merged",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c82005d35c4a0236990d1b314ee77b78525282d97754aa5c234196a2b4eb1b0f
+oid sha256:6491afa25bb1e6ab420090ee68bd83ba83771fe1fc329262269045b95a7a7633
 size 18915424

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5950483c68653acb7a7de98acb32114f76cf80909161f3cd25a9add4cf2ccb1
+oid sha256:ac76366239e5a8083e16682ca6d05e02674ff2b29a3e4778e698186a59f7b74b
 size 5368