first commit

README.md

@@ -1,3 +1,71 @@
-# fish-speech-1.5_a14145515045515264908091
+---
+tags:
+- text-to-speech
+license: cc-by-nc-sa-4.0
+language:
+- zh
+- en
+- de
+- ja
+- fr
+- es
+- ko
+- ar
+- nl
+- ru
+- it
+- pl
+- pt
+pipeline_tag: text-to-speech
+inference: false
+extra_gated_prompt: >-
+  You agree to not use the model to generate contents that violate DMCA or local
+  laws.
+extra_gated_fields:
+  Country: country
+  Specific date: date_picker
+  I agree to use this model for non-commercial use ONLY: checkbox
+---
 
-fish-speech-1.5
+
+# Fish Speech V1.5
+
+**Fish Speech V1.5** is a leading text-to-speech (TTS) model trained on more than 1 million hours of audio data in multiple languages.
+
+Supported languages:
+- English (en) >300k hours
+- Chinese (zh) >300k hours
+- Japanese (ja) >100k hours
+- German (de) ~20k hours
+- French (fr) ~20k hours
+- Spanish (es) ~20k hours
+- Korean (ko) ~20k hours
+- Arabic (ar) ~20k hours
+- Russian (ru) ~20k hours
+- Dutch (nl) <10k hours
+- Italian (it) <10k hours
+- Polish (pl) <10k hours
+- Portuguese (pt) <10k hours
+
+Please refer to [Fish Speech Github](https://github.com/fishaudio/fish-speech) for more info.  
+Demo available at [Fish Audio](https://fish.audio/).
+
+## Citation
+
+If you found this repository useful, please consider citing this work:
+
+```
+@misc{fish-speech-v1.4,
+      title={Fish-Speech: Leveraging Large Language Models for Advanced Multilingual Text-to-Speech Synthesis}, 
+      author={Shijia Liao and Yuxuan Wang and Tianyu Li and Yifan Cheng and Ruoyi Zhang and Rongzhi Zhou and Yijin Xing},
+      year={2024},
+      eprint={2411.01156},
+      archivePrefix={arXiv},
+      primaryClass={cs.SD},
+      url={https://arxiv.org/abs/2411.01156}, 
+}
+```
+
+## License
+
+This model is permissively licensed under the BY-CC-NC-SA-4.0 license.

config.json

@@ -0,0 +1,28 @@
+{
+    "attention_qkv_bias": false,
+    "codebook_size": 1024,
+    "dim": 1024,
+    "dropout": 0.0,
+    "fast_attention_qkv_bias": false,
+    "fast_dim": 1024,
+    "fast_head_dim": 64,
+    "fast_intermediate_size": 4096,
+    "fast_n_head": 16,
+    "fast_n_local_heads": 2,
+    "head_dim": 64,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "is_reward_model": false,
+    "max_seq_len": 8192,
+    "model_type": "dual_ar",
+    "n_fast_layer": 4,
+    "n_head": 16,
+    "n_layer": 24,
+    "n_local_heads": 2,
+    "norm_eps": 1e-06,
+    "num_codebooks": 8,
+    "rope_base": 1000000.0,
+    "tie_word_embeddings": false,
+    "use_gradient_checkpointing": true,
+    "vocab_size": 102048
+}

configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-to-speech", "allow_remote": true}