Text-to-Speech
VoxCPM
Safetensors
English
tts
lora
single-speaker
audio
alejandro-hp commited on
Commit
8283dfb
·
verified ·
1 Parent(s): d959d49

Model card: link training dataset

Browse files
Files changed (1) hide show
  1. README.md +3 -0
README.md CHANGED
@@ -6,6 +6,8 @@ library_name: voxcpm
6
  pipeline_tag: text-to-speech
7
  base_model: openbmb/VoxCPM2
8
  base_model_relation: finetune
 
 
9
  tags:
10
  - text-to-speech
11
  - tts
@@ -80,6 +82,7 @@ Tips:
80
  | Weights | bf16 safetensors, ~4.6 GB, plus the unchanged base audio codec (`audiovae.pth`) |
81
 
82
  ### Training data
 
83
  ~47 minutes (854 clips) of purpose-made recordings by the voice owner, captured with a Shure MV7+ at
84
  48 kHz / 24-bit: phonetically balanced read sentences (CMU ARCTIC prompts), conversational and
85
  stream-style lines (greetings, reactions, hype, calm), math explanations, and lines containing the
 
6
  pipeline_tag: text-to-speech
7
  base_model: openbmb/VoxCPM2
8
  base_model_relation: finetune
9
+ datasets:
10
+ - alejandro-hp/AlephTTS-data
11
  tags:
12
  - text-to-speech
13
  - tts
 
82
  | Weights | bf16 safetensors, ~4.6 GB, plus the unchanged base audio codec (`audiovae.pth`) |
83
 
84
  ### Training data
85
+ [alejandro-hp/AlephTTS-data](https://huggingface.co/datasets/alejandro-hp/AlephTTS-data) (CC0-1.0):
86
  ~47 minutes (854 clips) of purpose-made recordings by the voice owner, captured with a Shure MV7+ at
87
  48 kHz / 24-bit: phonetically balanced read sentences (CMU ARCTIC prompts), conversational and
88
  stream-style lines (greetings, reactions, hype, calm), math explanations, and lines containing the