End of training

README.md

@@ -2,6 +2,7 @@
 license: mit
 base_model: microsoft/speecht5_tts
 tags:
+- text-to-speech
 - generated_from_trainer
 datasets:
 - facebook/voxpopuli_sl
@@ -17,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the voxpopuli dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4666
+- Loss: 0.4380
 
 ## Model description
 
@@ -44,16 +45,16 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 500
-- training_steps: 2000
+- lr_scheduler_warmup_steps: 50
+- training_steps: 100
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.4942        | 25.64 | 1000 | 0.4706          |
-| 0.474         | 51.28 | 2000 | 0.4666          |
+| 0.4788        | 1.28  | 50   | 0.4381          |
+| 0.4788        | 2.56  | 100  | 0.4380          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12b3b7c9496b9dc5a9926d2a50226f84e78c167a26d2b61bb61ccb8306748b80
+oid sha256:b81be39a5ad7c7f482fbd029374d24176ec20cde98bcb3f42798d2a57bcbb896
 size 577789320

runs/Feb20_09-31-48_e76f989df546/events.out.tfevents.1708421509.e76f989df546.920.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff674a8124202c4a59a1f61dc2b7a8246ed253d53af9f781a34827e335eef929
-size 6936
+oid sha256:982f9d3dc1e06f56255e485f0fab6215e08b68e4120c8fc48a6cc9b9f7169f91
+size 7964