Unverified Commit 8e465f1b authored by Yoach Lacombe's avatar Yoach Lacombe Committed by GitHub
Browse files

Update training guide colab (#108)

* Update README.md

* Update README.md

* Update README.md

* update configs and readme

* fix training and eval single gpus and long audios errors

* fix error transcriptions none

* fix trascription null wer

* Update README.md

* Update README.md

---------

Co-authored-by: yoach@huggingface.co <Yoach Lacombe>
parent 8f5ef3a2
...@@ -119,7 +119,7 @@ https://github.com/huggingface/parler-tts/assets/52246514/251e2488-fe6e-42c1-81c ...@@ -119,7 +119,7 @@ https://github.com/huggingface/parler-tts/assets/52246514/251e2488-fe6e-42c1-81c
## Training ## Training
<a target="_blank" href="https://colab.research.google.com/github/ylacombe/scripts_and_notebooks/blob/main/Finetuning_Parler_TTS_on_a_single_speaker_dataset.ipynb"> <a target="_blank" href="https://github.com/ylacombe/scripts_and_notebooks/blob/main/Finetuning_Parler_TTS_v1_on_a_single_speaker_dataset.ipynb">
<img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/> <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/>
</a> </a>
...@@ -136,7 +136,7 @@ accelerate launch ./training/run_parler_tts_training.py ./helpers/training_confi ...@@ -136,7 +136,7 @@ accelerate launch ./training/run_parler_tts_training.py ./helpers/training_confi
``` ```
> [!IMPORTANT] > [!IMPORTANT]
> You can also follow [this fine-tuning guide](https://colab.research.google.com/github/ylacombe/scripts_and_notebooks/blob/main/Finetuning_Parler_TTS_on_a_single_speaker_dataset.ipynb) on a mono-speaker dataset example. > You can also follow [this fine-tuning guide](https://github.com/ylacombe/scripts_and_notebooks/blob/main/Finetuning_Parler_TTS_v1_on_a_single_speaker_dataset.ipynb) on a mono-speaker dataset example.
## Acknowledgements ## Acknowledgements
......
# Training Parler-TTS # Training Parler-TTS
<a target="_blank" href="https://colab.research.google.com/github/ylacombe/scripts_and_notebooks/blob/main/Finetuning_Parler_TTS_on_a_single_speaker_dataset.ipynb"> <a target="_blank" href="https://github.com/ylacombe/scripts_and_notebooks/blob/main/Finetuning_Parler_TTS_v1_on_a_single_speaker_dataset.ipynb">
<img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/> <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/>
</a> </a>
...@@ -18,7 +18,7 @@ This sub-folder contains all the information to train or fine-tune your own Parl ...@@ -18,7 +18,7 @@ This sub-folder contains all the information to train or fine-tune your own Parl
- [3. Training guide](#c-training) - [3. Training guide](#c-training)
> [!IMPORTANT] > [!IMPORTANT]
> You can also follow [this fine-tuning guide](https://colab.research.google.com/github/ylacombe/scripts_and_notebooks/blob/main/Finetuning_Parler_TTS_on_a_single_speaker_dataset.ipynb) on a mono-speaker dataset example. > You can also follow [this fine-tuning guide](https://github.com/ylacombe/scripts_and_notebooks/blob/main/Finetuning_Parler_TTS_v1_on_a_single_speaker_dataset.ipynb) on a mono-speaker dataset example.
## 1. Architecture ## 1. Architecture
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment