faster-whisper-medium-chichewa

README.md

@@ -4,8 +4,6 @@ license: apache-2.0
 base_model: openai/whisper-medium
 tags:
 - generated_from_trainer
-metrics:
-- wer
 model-index:
 - name: medium-model
   results: []
@@ -18,9 +16,14 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.2383
-- Wer: 0.6660
-- Cer: 0.2985
+- eval_loss: 1.2478
+- eval_wer: 0.4493
+- eval_cer: 0.1448
+- eval_runtime: 110.1443
+- eval_samples_per_second: 0.844
+- eval_steps_per_second: 0.109
+- epoch: 53.5714
+- step: 3000
 
 ## Model description
 
@@ -40,28 +43,17 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 1e-05
-- train_batch_size: 2
+- train_batch_size: 4
 - eval_batch_size: 8
 - seed: 42
 - gradient_accumulation_steps: 2
-- total_train_batch_size: 4
+- total_train_batch_size: 8
 - 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: cosine
 - lr_scheduler_warmup_steps: 500
 - training_steps: 5000
 - mixed_precision_training: Native AMP
 
-### Training results
-
-| Training Loss | Epoch   | Step | Validation Loss | Wer    | Cer    |
-|:-------------:|:-------:|:----:|:---------------:|:------:|:------:|
-| 0.0575        | 13.1579 | 1000 | 1.9806          | 0.6920 | 0.3415 |
-| 0.0118        | 26.3158 | 2000 | 2.0510          | 0.6764 | 0.3321 |
-| 0.0039        | 39.4737 | 3000 | 2.1584          | 0.6647 | 0.2982 |
-| 0.0011        | 52.6316 | 4000 | 2.2279          | 0.6997 | 0.3405 |
-| 0.0009        | 65.7895 | 5000 | 2.2383          | 0.6660 | 0.2985 |
-
-
 ### Framework versions
 
 - Transformers 4.48.0

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb3cabbf5fb0424ff63ab7230121e01a041e7c7521d32fac4482092cc583fd70
+oid sha256:6d126b359f60efb34b8925f392dd9d2e4f24529e435712b5eea78cb8e622d015
 size 3055544304

runs/Nov13_18-37-10_88fd4ec48df0/events.out.tfevents.1763059054.88fd4ec48df0.333.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:081dae34a92f5c2e952232e83a5a185fcd8f046bdbf0aa2da705c91195d4c7e4
+size 20604

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3b243009ae2adc29d06fdcfe6aa897dec00a74ccf2d7e238f906a91388ecb71
+oid sha256:434963b0db0b4e5b80da86ffac3c9a125d7a97ac9d48a17c83d5a7b0990944dd
 size 5905