razhan
/

whisper-base-me

@@ -16,23 +16,23 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 4.1443
-- Mazanderani Wer: 1.1377
-- Mazanderani Cer: 0.7784
-- Gilaki Wer: 1.2232
-- Gilaki Cer: 0.8535
-- Zazaki Wer: 1.2574
-- Zazaki Cer: 0.8634
-- Laki Kurdish Wer: 1.0568
-- Laki Kurdish Cer: 0.8054
-- Talysh Wer: 1.0
-- Talysh Cer: 0.8333
-- Hawrami Wer: 1.0632
-- Hawrami Cer: 0.7705
-- Southern Kurdish Wer: 1.6039
-- Southern Kurdish Cer: 1.0439
-- Avg Wer: 1.1917
-- Avg Cer: 0.8498
 ## Model description
@@ -52,7 +52,7 @@ More information needed
 The following hyperparameters were used during training:
 - learning_rate: 1e-05
-- train_batch_size: 256
 - eval_batch_size: 128
 - seed: 42
 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
@@ -65,10 +65,10 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss | Mazanderani Wer | Mazanderani Cer | Gilaki Wer | Gilaki Cer | Zazaki Wer | Zazaki Cer | Laki Kurdish Wer | Laki Kurdish Cer | Talysh Wer | Talysh Cer | Hawrami Wer | Hawrami Cer | Southern Kurdish Wer | Southern Kurdish Cer | Avg Wer | Avg Cer |
 |:-------------:|:-----:|:----:|:---------------:|:---------------:|:---------------:|:----------:|:----------:|:----------:|:----------:|:----------------:|:----------------:|:----------:|:----------:|:-----------:|:-----------:|:--------------------:|:--------------------:|:-------:|:-------:|
-| No log        | 1.0   | 4    | 4.3810          | 1.4671          | 1.0317          | 1.3956     | 1.0145     | 1.2574     | 0.8624     | 1.0669           | 0.8138           | 1.0        | 0.875      | 1.0632      | 0.7736      | 1.6118               | 1.0330               | 1.2660  | 0.9149  |
-| No log        | 2.0   | 8    | 4.3746          | 1.4671          | 1.0430          | 1.2142     | 0.8587     | 1.2574     | 0.8609     | 1.0649           | 0.8070           | 1.0        | 0.875      | 1.0632      | 0.7736      | 1.6098               | 1.0326               | 1.2395  | 0.8930  |
-| No log        | 3.0   | 12   | 4.3250          | 1.4611          | 1.0388          | 1.2178     | 0.8595     | 1.2574     | 0.8609     | 1.0629           | 0.8086           | 1.0        | 0.8333     | 1.0675      | 0.7744      | 1.6078               | 1.0326               | 1.2392  | 0.8869  |
-| No log        | 4.0   | 16   | 4.1443          | 1.1377          | 0.7784          | 1.2232     | 0.8535     | 1.2574     | 0.8634     | 1.0568           | 0.8054           | 1.0        | 0.8333     | 1.0632      | 0.7705      | 1.6039               | 1.0439               | 1.1917  | 0.8498  |
 ### Framework versions

 This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the None dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.5421
+- Mazanderani Wer: 0.6836
+- Mazanderani Cer: 0.2510
+- Gilaki Wer: 0.9606
+- Gilaki Cer: 0.3818
+- Zazaki Wer: 0.7623
+- Zazaki Cer: 0.3182
+- Laki Kurdish Wer: 0.6037
+- Laki Kurdish Cer: 0.1653
+- Talysh Wer: 0.9167
+- Talysh Cer: 0.5
+- Hawrami Wer: 0.4145
+- Hawrami Cer: 0.0865
+- Southern Kurdish Wer: 0.5610
+- Southern Kurdish Cer: 0.1721
+- Avg Wer: 0.7003
+- Avg Cer: 0.2678
 ## Model description
 The following hyperparameters were used during training:
 - learning_rate: 1e-05
+- train_batch_size: 128
 - eval_batch_size: 128
 - seed: 42
 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 | Training Loss | Epoch | Step | Validation Loss | Mazanderani Wer | Mazanderani Cer | Gilaki Wer | Gilaki Cer | Zazaki Wer | Zazaki Cer | Laki Kurdish Wer | Laki Kurdish Cer | Talysh Wer | Talysh Cer | Hawrami Wer | Hawrami Cer | Southern Kurdish Wer | Southern Kurdish Cer | Avg Wer | Avg Cer |
 |:-------------:|:-----:|:----:|:---------------:|:---------------:|:---------------:|:----------:|:----------:|:----------:|:----------:|:----------------:|:----------------:|:----------:|:----------:|:-----------:|:-----------:|:--------------------:|:--------------------:|:-------:|:-------:|
+| 0.5933        | 1.0   | 164  | 0.7337          | 0.8884          | 0.3139          | 0.9969     | 0.3853     | 0.9485     | 0.7335     | 0.7857           | 0.2461           | 0.9167     | 0.5        | 0.5257      | 0.1162      | 0.6900               | 0.2137               | 0.8217  | 0.3584  |
+| 0.4436        | 2.0   | 328  | 0.5930          | 0.7514          | 0.2939          | 0.9723     | 0.3818     | 0.8382     | 0.4153     | 0.6487           | 0.1846           | 0.9167     | 0.5        | 0.4419      | 0.0933      | 0.5951               | 0.1798               | 0.7378  | 0.2927  |
+| 0.387         | 3.0   | 492  | 0.5509          | 0.6821          | 0.2436          | 0.9523     | 0.3735     | 0.7892     | 0.3340     | 0.6094           | 0.1678           | 0.9167     | 0.5        | 0.4230      | 0.0891      | 0.5705               | 0.1871               | 0.7062  | 0.2707  |
+| 0.3575        | 4.0   | 656  | 0.5421          | 0.6836          | 0.2510          | 0.9606     | 0.3818     | 0.7623     | 0.3182     | 0.6037           | 0.1653           | 0.9167     | 0.5        | 0.4145      | 0.0865      | 0.5610               | 0.1721               | 0.7003  | 0.2678  |
 ### Framework versions