Update README.md

README.md

@@ -14,6 +14,7 @@ This repository contains a fine-tuned version of Facebook's MMS-TTS model, adapt
 
 - 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
+- Training steps: 5,100
 - Speaker: Sokhov Murat
 - Language: Circassian (Kabardian)
 
@@ -39,7 +40,7 @@ This code will generate an audio file `finetuned_output.wav` containing the spee
 
 ## 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.
+- Since no pre-trained MMS-TTS model is available for Kabardian, we fine-tuned a model for Chechen, which has the closest character set to Kabardian.
 - 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