update model card README.md

README.md

@@ -1,6 +1,6 @@
 ---
-license: mit
-base_model: microsoft/speecht5_tts
+license: apache-2.0
+base_model: speechbrain/spkrec-xvect-voxceleb
 tags:
 - generated_from_trainer
 datasets:
@@ -15,9 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # speecht5_finetuned_voxpopuli_en
 
-This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the facebook/voxpopuli dataset.
+This model is a fine-tuned version of [speechbrain/spkrec-xvect-voxceleb](https://huggingface.co/speechbrain/spkrec-xvect-voxceleb) on the facebook/voxpopuli dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6375
+- Loss: 0.6952
 
 ## Model description
 
@@ -45,15 +45,14 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 10
-- training_steps: 30
+- training_steps: 20
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.8412        | 0.12  | 10   | 0.7213          |
-| 0.7107        | 0.24  | 20   | 0.6504          |
-| 0.7161        | 0.35  | 30   | 0.6375          |
+| 0.7848        | 0.12  | 10   | 0.7479          |
+| 0.7404        | 0.24  | 20   | 0.6952          |
 
 
 ### Framework versions