Update README.md

Updated model names, epochs and last results

README.md

@@ -62,7 +62,7 @@ All samples were resampled to 24kHz.
 <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
 
 The model in this repository (styletts2-spanish-multispeaker) was [trained from scratch](https://github.com/yl4579/StyleTTS2#training).
-Two other models (multispeaker_plbert_subword_asr) were [fine-tuned](https://github.com/yl4579/StyleTTS2#finetuning) for comparison and evaluation.
+Two other models (FT-libri-tts_asr-es_pl-bert-subword-es_wavlm-base-plus and FT-kokoro_asr-es_pl-bert-subword-es_wavlm-base-plus) were [fine-tuned](https://github.com/yl4579/StyleTTS2#finetuning) for comparison and evaluation.
 The [original pitch extractor](https://github.com/yl4579/StyleTTS2#pre-trained-modules) was used for all models. 
 A Spanish [AuxiliaryASR](https://github.com/yl4579/AuxiliaryASR) was trained as text aligner and used for all models.
 [BSC-LT/PL-BERT-wp-es](https://huggingface.co/BSC-LT/PL-BERT-wp-es) was used as prosodic text Encoder for all models.
@@ -70,21 +70,21 @@ A Spanish [AuxiliaryASR](https://github.com/yl4579/AuxiliaryASR) was trained as
 
 styletts2-spanish-multispeaker was trained from scratch.
 The first stage was executed for 99 epochs.
-The second stage was executed for 34 epochs.
+The second stage was executed for 86 epochs.
 
-multispeaker_plbert_subword_asr was fine-tuned and [yl4579/StyleTTS2-LibriTTS](https://huggingface.co/yl4579/StyleTTS2-LibriTTS) was used as pre-trained model.
+FT-libri-tts_asr-es_pl-bert-subword-es_wavlm-base-plus was fine-tuned and [yl4579/StyleTTS2-LibriTTS](https://huggingface.co/yl4579/StyleTTS2-LibriTTS) was used as pre-trained model.
 The fine-tuning stage was executed for 32 epochs.
 
-multispeaker_FT_kokoro was fine-tuned and [hexgrad/Kokoro-82M](https://huggingface.co/hexgrad/Kokoro-82M) was used as pre-trained model.
+FT-kokoro_asr-es_pl-bert-subword-es_wavlm-base-plus was fine-tuned and [hexgrad/Kokoro-82M](https://huggingface.co/hexgrad/Kokoro-82M) was used as pre-trained model.
 The fine-tuning stage was executed for 79 epochs.
 
 ### Training Hyperparameters
 
 styletts2-spanish-multispeaker first stage hyperparameters can be found [here](https://huggingface.co/langtech-veu/styletts2-spanish-multispeaker/blob/main/1_config_styletts2-spanish-multispeaker_1st_phase.yml) and second stage hyperparameters [here](https://huggingface.co/langtech-veu/styletts2-spanish-multispeaker/blob/main/1_config_styletts2-spanish-multispeaker_2nd_phase.yml).
 
-multispeaker_plbert_subword_asr fine-tuning hyperparameters can be found [here](https://huggingface.co/langtech-veu/styletts2-spanish-multispeaker/blob/main/2_multispeaker_plbert_subword_asr.yml).
+FT-libri-tts_asr-es_pl-bert-subword-es_wavlm-base-plus fine-tuning hyperparameters can be found [here](https://huggingface.co/langtech-veu/styletts2-spanish-multispeaker/blob/main/FT-libri-tts_asr-es_pl-bert-subword-es_wavlm-base-plus.yml).
 
-multispeaker_FT_kokoro fine-tuning hyperparameters can be found [here](https://huggingface.co/langtech-veu/styletts2-spanish-multispeaker/blob/main/3_multispeaker_FT_kokoro.yml).
+FT-kokoro_asr-es_pl-bert-subword-es_wavlm-base-plus fine-tuning hyperparameters can be found [here](https://huggingface.co/langtech-veu/styletts2-spanish-multispeaker/blob/main/FT-kokoro_asr-es_pl-bert-subword-es_wavlm-base-plus.yml).
 ## Evaluation
 
 <!-- This section describes the evaluation protocols and provides the results. -->
@@ -119,12 +119,9 @@ The model in this repository (styletts2-spanish-multispeaker) has been compared
 
 |                             Model                     | UTMOS | DNSMOS Pro BVCC |  WER  |
 |:-----------------------------------------------------:|:-----:|:---------------:|:-----:|
-| **styletts2-spanish-multispeaker**                    | 3.043 | 2.609           | 0.215 |
-| FT-libri-tts_asr-es_pl-bert-subword-es_wavlm-base-plus| 3.839 | 2.552           | 0.204 |
-| FT-kokoro_asr-es_pl-bert-subword-es_wavlm-base-plus   | 1.489 | 1.839           | 0.365 |
-| PT_asr-es_pl-bert-subword-es_wavlm-base-plus          | 3.170 | 2.741           | 0.197 |
-
-
+| **styletts2-spanish-multispeaker**                    | 3.170 | 2.741           | 0.197 |
+| FT-libri-tts_asr-es_pl-bert-subword-es_wavlm-base-plus| 3.043 | 2.552           | 0.204 |
+| FT-kokoro_asr-es_pl-bert-subword-es_wavlm-base-plus   | 1.569 | 1.918           | 0.390 |
 
 
 ## Additional Information