IOTEverythin
/

roxi-tts-pro

feature-extraction

speech-synthesis

voice-assistant

customer-support

Eval Results (legacy)

Model card Files Files and versions

Joshuant commited on Jul 3

Commit

27eff36

·

verified ·

1 Parent(s): 883717b

update name to roxi-tts-pro

Files changed (1) hide show

README.md +4 -4

README.md CHANGED Viewed

@@ -13,7 +13,7 @@ tags:
 - lora
 - voice-agent
 model-index:
-- name: roxi-tts-v3.1-1.7b
   results:
   - task:
       type: text-to-speech
@@ -27,7 +27,7 @@ model-index:
       value: 0.18
 ---
-# Roxi-TTS v3.1 (1.7B), Indian-English voice
 A larger, higher-fidelity member of the Roxi-TTS line. This is a LoRA fine-tune of the
 1.7B MOSS-TTS-Local-Transformer on about 4 hours of a single studio speaker, producing a
@@ -80,7 +80,7 @@ sys.path.insert(0, "MOSS-TTS")  # cloned repo, provides moss_tts_local
 from transformers import AutoProcessor
 from moss_tts_local.modeling_moss_tts import MossTTSDelayModel
-repo = "IOTEverythin/roxi-tts-v3.1-1.7b"
 device = "cuda" if torch.cuda.is_available() else "cpu"
 dtype = torch.bfloat16 if device == "cuda" else torch.float32
@@ -119,7 +119,7 @@ max_new_tokens far above the default, since the codec decode grows quadratically
 | roxi-tts-v2 | MOSS-TTS-Nano 0.1B | 0.96 | 0.26 | speaker A, about 50 min |
 | roxi-tts-v3 | MOSS-TTS-Nano 0.1B | 0.96 | 0.29 | speaker B, about 70 min |
 | roxi-tts-v3.1 | MOSS-TTS-Nano 0.1B | 0.96 | 0.33 | speaker B, about 4 hours |
-| roxi-tts-v3.1-1.7b (this) | MOSS-TTS-Local 1.7B | 0.97 | 0.18 | speaker B, about 4 hours, most intelligible |
 ## Training

 - lora
 - voice-agent
 model-index:
+- name: roxi-tts-pro
   results:
   - task:
       type: text-to-speech
       value: 0.18
 ---
+# Roxi-TTS Pro (1.7B), Indian-English voice
 A larger, higher-fidelity member of the Roxi-TTS line. This is a LoRA fine-tune of the
 1.7B MOSS-TTS-Local-Transformer on about 4 hours of a single studio speaker, producing a
 from transformers import AutoProcessor
 from moss_tts_local.modeling_moss_tts import MossTTSDelayModel
+repo = "IOTEverythin/roxi-tts-pro"
 device = "cuda" if torch.cuda.is_available() else "cpu"
 dtype = torch.bfloat16 if device == "cuda" else torch.float32
 | roxi-tts-v2 | MOSS-TTS-Nano 0.1B | 0.96 | 0.26 | speaker A, about 50 min |
 | roxi-tts-v3 | MOSS-TTS-Nano 0.1B | 0.96 | 0.29 | speaker B, about 70 min |
 | roxi-tts-v3.1 | MOSS-TTS-Nano 0.1B | 0.96 | 0.33 | speaker B, about 4 hours |
+| roxi-tts-pro (this) | MOSS-TTS-Local 1.7B | 0.97 | 0.18 | speaker B, about 4 hours, most intelligible |
 ## Training