End of training

README.md

@@ -16,7 +16,7 @@ datasets:
 metrics:
 - wer
 model-index:
-- name: SPEAK-ASR/whisper-si-exp-6
+- name: SPEAK-ASR/whisper-si-exp-7
   results:
   - task:
       type: automatic-speech-recognition
@@ -29,19 +29,19 @@ model-index:
       args: 'config: si, split: test'
     metrics:
     - type: wer
-      value: 21.23753159671243
+      value: 20.728200160443187
       name: Wer
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# SPEAK-ASR/whisper-si-exp-6
+# SPEAK-ASR/whisper-si-exp-7
 
 This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the SPEAK-ASR/openslr-sinhala-asr-preprocessed-1 | SPEAK-ASR/openslr-sinhala-asr-preprocessed-2 | SPEAK-ASR/openslr-sinhala-asr-preprocessed-3 | SPEAK-ASR/youtube-sinhala-asr-preprocessed dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1620
-- Wer: 21.2375
+- Loss: 0.1581
+- Wer: 20.7282
 
 ## Model description
 
@@ -71,7 +71,7 @@ The following hyperparameters were used during training:
 - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 1000
-- num_epochs: 15.0
+- num_epochs: 20.0
 
 ### Training results
 
@@ -88,6 +88,10 @@ The following hyperparameters were used during training:
 | 0.6370        | 11.4796 | 13500 | 0.1652          | 21.7635 |
 | 0.6355        | 12.7551 | 15000 | 0.1632          | 21.4154 |
 | 0.6367        | 14.0306 | 16500 | 0.1620          | 21.2375 |
+| 0.6320        | 15.3061 | 18000 | 0.1622          | 21.2300 |
+| 0.6196        | 16.5816 | 19500 | 0.1600          | 21.0468 |
+| 0.6069        | 17.8571 | 21000 | 0.1590          | 20.8690 |
+| 0.6063        | 19.1327 | 22500 | 0.1581          | 20.7282 |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff8cc317ede671fadea38518e0eaeb1bd94ef6b802986faa1962d633c819ac34
+oid sha256:82793ee169b59a032f801b87daa65db27dda1007d00b64ff1990fee5cf659bfb
 size 14176064