Create README.md

README.md

@@ -0,0 +1,52 @@
+---
+license: cc-by-nc-4.0
+language:
+- kbd
+datasets:
+- anzorq/kbd_speech
+pipeline_tag: text-to-speech
+---
+# MMS-TTS Fine-tuned for Kabardian (Speaker: Sokhov Murat)
+
+This repository contains a fine-tuned version of Facebook's MMS-TTS model, adapted for generating speech in the Kabardian language. The model is trained on a dataset of audio recordings by the speaker Sokhov Murat.
+
+## Model Details
+
+- Base Model: [facebook/mms-tts](https://huggingface.co/facebook/mms-tts)
+- Fine-tuned on: [anzorq/kbd_speech](https://huggingface.co/datasets/anzorq/kbd_speech) dataset
+- Speaker: Sokhov Murat
+- Language: Circassian (Kabardian)
+
+## Usage
+
+To use this model for text-to-speech generation, you can leverage the `pipeline` functionality from the Transformers library. Here's an example:
+
+```python
+from transformers import pipeline
+import scipy
+
+model_id = "anzorq/mms_finetune_kbd_murat"
+synthesiser = pipeline("text-to-speech", model_id, device=0) # add device=0 if you want to use a GPU
+
+text = "дауэ ущыт?"
+speech = synthesiser(text)
+
+# Save the generated audio to a file
+scipy.io.wavfile.write("finetuned_output.wav", rate=speech["sampling_rate"], data=speech["audio"][0])
+```
+
+This code will generate an audio file `finetuned_output.wav` containing the speech synthesis for the provided Kabardian text.
+
+## Notes
+
+- Since there is no pre-trained checkpoint for Kabardian in the original MMS-TTS model, a pre-trained checkpoint for a language with the closest character set (Chechen) was used for fine-tuning.
+- This model's performance is considerably worse than that of the fine-tuned VITS model [anzorq/kbd-vits-tts-male](https://huggingface.co/anzorq/kbd-vits-tts-male) for Kabardian text-to-speech.
+
+## License
+
+The original MMS-TTS model by Meta is licensed under the CC-BY-NC-4.0 License. This fine-tuned version inherits the same license.
+
+## Acknowledgments
+
+- [AI at Meta](https://ai.meta.com//) for the original MMS-TTS model.
+- [Sokhov Murat](https://www.instagram.com/carbatay) for providing the audio recordings used for fine-tuning.