End of training

README.md

@@ -0,0 +1,69 @@
+---
+library_name: transformers
+language:
+- pt
+license: mit
+base_model: microsoft/speecht5_tts
+tags:
+- generated_from_trainer
+datasets:
+- ylacombe/cml-tts
+model-index:
+- name: SpeechT5 Pt - Samuel Silva
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# SpeechT5 Pt - Samuel Silva
+
+This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the CML-TTS dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5228
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-05
+- train_batch_size: 4
+- eval_batch_size: 2
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 32
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+- training_steps: 4000
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch    | Step | Validation Loss |
+|:-------------:|:--------:|:----:|:---------------:|
+| 0.5126        | 33.3333  | 1000 | 0.5025          |
+| 0.4915        | 66.6667  | 2000 | 0.5113          |
+| 0.4796        | 100.0    | 3000 | 0.5199          |
+| 0.4655        | 133.3333 | 4000 | 0.5228          |
+
+
+### Framework versions
+
+- Transformers 4.47.0
+- Pytorch 2.5.1+cu121
+- Datasets 3.3.1
+- Tokenizers 0.21.0

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": "4.47.0"
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14a4aad27c914a7ca5868e1f102dac9ce0b63bca47b5b7ee1937db1d2cb80f82
+oid sha256:6efd97753fc7ad51ed61256a2fc25ddcbd6ef40e66abcaf92c604c6dd5457ecc
 size 577789320