bhattasp
/

better_transcription

Model card Files Files and versions Community

bhattasp commited on 15 days ago

Commit

090c84c

•

1 Parent(s): cfcf1e9

Upload folder using huggingface_hub

Files changed (2) hide show

README.md +4 -4
model.safetensors +1 -1

README.md CHANGED Viewed

@@ -14,10 +14,10 @@ model_type: t5
 This model combines transcriptions from multiple sources to generate an optimal transcription. It is fine-tuned on a dataset where each sample has three candidate transcriptions and a reference transcription.
 ### Training Details
-Model trained on 5000 samples for 10 epochs with T5-small as the base model.
-Training Loss: 0.0054761185310781
 ### Evaluation Details
-Test Loss: 0.021037305083354822
-Word Error Rate (WER): 0.17595307917888564

 This model combines transcriptions from multiple sources to generate an optimal transcription. It is fine-tuned on a dataset where each sample has three candidate transcriptions and a reference transcription.
 ### Training Details
+Model trained on 9000 samples for 10 epochs with T5-small as the base model.
+Training Loss: 0.01410862896591425
 ### Evaluation Details
+Test Loss: 0.009594996869187836
+Word Error Rate (WER): 0.08080686073197246

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4a7e40657464e863d80b13ac6bac138a7d6f55029df2776896b195e45107d77
 size 242041896

 version https://git-lfs.github.com/spec/v1
+oid sha256:99de6e01d15e2551b45894fb122b47a6e83ee41e9dd89cdaa8b058dc8b037de5
 size 242041896