Model save

README.md

@@ -1,4 +1,6 @@
 ---
+license: apache-2.0
+base_model: openai/whisper-tiny
 tags:
 - generated_from_trainer
 metrics:
@@ -13,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # whisper-tiny-hi2_test
 
-This model was trained from scratch on the None dataset.
+This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5291
-- Wer: 63.6040
+- Loss: 0.6051
+- Wer: 70.0398
 
 ## Model description
 
@@ -40,8 +42,7 @@ The following hyperparameters were used during training:
 - eval_batch_size: 1
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: constant
-- lr_scheduler_warmup_steps: 50
+- lr_scheduler_type: linear
 - training_steps: 200
 - mixed_precision_training: Native AMP
 
@@ -49,11 +50,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Wer     |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|
-| 1.1887        | 1.25  | 40   | 0.9954          | 87.2978 |
-| 0.6663        | 2.5   | 80   | 0.6781          | 73.2916 |
-| 0.5053        | 3.75  | 120  | 0.5858          | 66.2291 |
-| 0.406         | 5.0   | 160  | 0.5440          | 66.1360 |
-| 0.3236        | 6.25  | 200  | 0.5291          | 63.6040 |
+| 1.2169        | 1.25  | 40   | 1.0360          | 91.6081 |
+| 0.7302        | 2.5   | 80   | 0.7369          | 79.8035 |
+| 0.5917        | 3.75  | 120  | 0.6505          | 69.9890 |
+| 0.5156        | 5.0   | 160  | 0.6157          | 70.4293 |
+| 0.481         | 6.25  | 200  | 0.6051          | 70.0398 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:764e4ed9e166dafd23099d01bb4f1db2f7c651336bf289c68445e3121ffade3c
+oid sha256:a59c8982089b3ffb0f35b2a8b93a329827d3603f741f4d47ddb7a17dc5a7e5e2
 size 151061672

whisper-tiny-hi-checkpoint-1/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65486a040e9edffe3575e458f27f57a36d8b2427a1a78dbd727b53bf7ff9bc9a
+oid sha256:a59c8982089b3ffb0f35b2a8b93a329827d3603f741f4d47ddb7a17dc5a7e5e2
 size 151061672

whisper-tiny-hi-checkpoint-1/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34b00aa1f8925d482dd1ad48e165b81cd8051f3b752e0716117669ce7c5b2e10
+oid sha256:8c982fa9327e2e49f4765e9f4a5be54ca2c672121610ce55b8168505a2beb3b7
 size 5240