Upload folder using huggingface_hub
Browse files- README.md +54 -0
- config.json +32 -0
- model.pth +3 -0
- special_tokens.json +0 -0
- tokenizer.tiktoken +0 -0
README.md
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- lb
|
| 4 |
+
tags:
|
| 5 |
+
- text-to-speech
|
| 6 |
+
- fish-speech
|
| 7 |
+
- luxembourgish
|
| 8 |
+
- tts
|
| 9 |
+
license: cc-by-nc-sa-4.0
|
| 10 |
+
datasets:
|
| 11 |
+
- denZLS/Luxembourgish-Male-TTS-for-LOD
|
| 12 |
+
base_model: fishaudio/openaudio-s1-mini
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
# Fish Speech - Luxembourgish TTS
|
| 16 |
+
|
| 17 |
+
Fine-tuned [Fish Speech](https://github.com/fishaudio/fish-speech) Dual-AR model for Luxembourgish text-to-speech.
|
| 18 |
+
|
| 19 |
+
## Model Details
|
| 20 |
+
|
| 21 |
+
- **Base Model:** [fishaudio/openaudio-s1-mini](https://huggingface.co/fishaudio/openaudio-s1-mini)
|
| 22 |
+
- **Architecture:** Dual-AR Transformer (860M parameters)
|
| 23 |
+
- **Language:** Luxembourgish (lb)
|
| 24 |
+
- **Training Data:** 32,000 samples from male Luxembourgish speaker
|
| 25 |
+
- **Training Steps:** 9,000 steps (~2.4 epochs)
|
| 26 |
+
- **Fine-tuned on:** NVIDIA RTX 5090
|
| 27 |
+
|
| 28 |
+
## Usage
|
| 29 |
+
|
| 30 |
+
Requires [Fish Speech](https://github.com/fishaudio/fish-speech) installed.
|
| 31 |
+
|
| 32 |
+
```bash
|
| 33 |
+
# WebUI
|
| 34 |
+
python tools/run_webui.py \
|
| 35 |
+
--llama-checkpoint-path vivienhenz/fish-speech-luxembourgish \
|
| 36 |
+
--decoder-checkpoint-path fishaudio/openaudio-s1-mini/codec.pth
|
| 37 |
+
```
|
| 38 |
+
|
| 39 |
+
## Training Details
|
| 40 |
+
|
| 41 |
+
- Dataset: 32,000 male voice samples (~28 hours)
|
| 42 |
+
- Optimizer: AdamW (lr=1e-4)
|
| 43 |
+
- Precision: bf16-mixed
|
| 44 |
+
- Training time: ~3 hours on RTX 5090
|
| 45 |
+
|
| 46 |
+
## Example
|
| 47 |
+
|
| 48 |
+
Input: `d'nottär huet haut de mueren zwou venten.`
|
| 49 |
+
|
| 50 |
+
Output: Natural Luxembourgish male voice
|
| 51 |
+
|
| 52 |
+
## License
|
| 53 |
+
|
| 54 |
+
CC-BY-NC-SA-4.0 (inherited from Fish Speech)
|
config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"attention_o_bias": false,
|
| 3 |
+
"attention_qk_norm": true,
|
| 4 |
+
"attention_qkv_bias": false,
|
| 5 |
+
"codebook_size": 4096,
|
| 6 |
+
"dim": 1024,
|
| 7 |
+
"dropout": 0.0,
|
| 8 |
+
"fast_attention_o_bias": false,
|
| 9 |
+
"fast_attention_qk_norm": false,
|
| 10 |
+
"fast_attention_qkv_bias": false,
|
| 11 |
+
"fast_dim": 1024,
|
| 12 |
+
"fast_head_dim": 64,
|
| 13 |
+
"fast_intermediate_size": 3072,
|
| 14 |
+
"fast_n_head": 16,
|
| 15 |
+
"fast_n_local_heads": 8,
|
| 16 |
+
"head_dim": 128,
|
| 17 |
+
"initializer_range": 0.03125,
|
| 18 |
+
"intermediate_size": 3072,
|
| 19 |
+
"max_seq_len": 8192,
|
| 20 |
+
"model_type": "dual_ar",
|
| 21 |
+
"n_fast_layer": 4,
|
| 22 |
+
"n_head": 16,
|
| 23 |
+
"n_layer": 28,
|
| 24 |
+
"n_local_heads": 8,
|
| 25 |
+
"norm_eps": 1e-06,
|
| 26 |
+
"num_codebooks": 10,
|
| 27 |
+
"rope_base": 1000000,
|
| 28 |
+
"scale_codebook_embeddings": true,
|
| 29 |
+
"tie_word_embeddings": false,
|
| 30 |
+
"use_gradient_checkpointing": true,
|
| 31 |
+
"vocab_size": 155776
|
| 32 |
+
}
|
model.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:006510c1f2d855aca83f6ad0e947fee94ea07be56d32a3f0783b4dfee4203c58
|
| 3 |
+
size 1720408503
|
special_tokens.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer.tiktoken
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|