End of training

README.md

@@ -18,6 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
 # SpeechT5 TTS Italian
 
 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: 0.5349
 
 ## Model description
 
@@ -47,6 +49,16 @@ The following hyperparameters were used during training:
 - lr_scheduler_warmup_steps: 500
 - training_steps: 4000
 
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.5293        | 60.61  | 1000 | 0.5201          |
+| 0.4921        | 121.21 | 2000 | 0.5254          |
+| 0.4913        | 181.82 | 3000 | 0.5318          |
+| 0.5048        | 242.42 | 4000 | 0.5349          |
+
+
 ### Framework versions
 
 - Transformers 4.32.0.dev0

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "eos_token_id": 2,
+  "max_length": 1876,
+  "pad_token_id": 1,
+  "transformers_version": "4.32.0.dev0"
+}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58244506e614ff4ec074a47ee28588a805c0fce6fa3c3a9447a5d39b24d7b9da
+oid sha256:b34fc80d1863182cd5a6b0c5d93f3b25065ea1fd6f80801a6d019319e6fd1691
 size 577878333