End of training

README.md

@@ -1,6 +1,6 @@
 ---
 license: mit
-base_model: microsoft/speecht5_tts
+base_model: jaymanvirk/speecht5_tts_finetuned_voxpopuli_lt
 tags:
 - generated_from_trainer
 datasets:
@@ -15,9 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # speecht5_tts_finetuned_voxpopuli_lt
 
-This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the voxpopuli dataset.
+This model is a fine-tuned version of [jaymanvirk/speecht5_tts_finetuned_voxpopuli_lt](https://huggingface.co/jaymanvirk/speecht5_tts_finetuned_voxpopuli_lt) on the voxpopuli dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5784
+- Loss: 0.4718
 
 ## Model description
 
@@ -44,18 +44,18 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 16
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 5
-- training_steps: 40
+- lr_scheduler_warmup_steps: 50
+- training_steps: 400
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 0.25  | 10   | 0.6428          |
-| No log        | 0.5   | 20   | 0.6082          |
-| 0.6736        | 1.1   | 30   | 0.5881          |
-| 0.6736        | 1.35  | 40   | 0.5784          |
+| 0.5879        | 3.06  | 100  | 0.5127          |
+| 0.5239        | 7.04  | 200  | 0.4850          |
+| 0.4996        | 11.04 | 300  | 0.4766          |
+| 0.4897        | 15.03 | 400  | 0.4718          |
 
 
 ### Framework versions

runs/Mar25_07-48-01_fc60ba0d7727/events.out.tfevents.1711352992.fc60ba0d7727.34.3

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84bada699a7f5b66ea75a291721ed0810185101449d43c8c8cbf02ffcd38964e
-size 8191
+oid sha256:e9c52d7a32b406777fab8ee5e92f6c8522b86ac1b7166b9976baf49027eb499c
+size 8545