bhattasp
/

better_transcription

Model card Files Files and versions Community

bhattasp commited on 14 days ago

Commit

cabea67

•

1 Parent(s): 090c84c

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 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

 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 21000 samples for 10 epochs with T5-small as the base model.
+Training Loss: 0.00022581950179301202
 ### Evaluation Details
+Test Loss: 0.011895381462127404
+Word Error Rate (WER): 0.07370435071957408

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99de6e01d15e2551b45894fb122b47a6e83ee41e9dd89cdaa8b058dc8b037de5
 size 242041896

 version https://git-lfs.github.com/spec/v1
+oid sha256:014a1dafdce536aedb9c8a10b55473f3d7270085b8ee40a8a28fad2ee0eb03ea
 size 242041896