Skip to content

Commit

Permalink
[docx]:delete speaker param in docs (#323)
Browse files Browse the repository at this point in the history
Co-authored-by: WhaleDolphin <[email protected]>
  • Loading branch information
Whale-Dolphin and Whale-Dolphin authored Jul 6, 2024
1 parent a4bd622 commit 3c526c6
Show file tree
Hide file tree
Showing 3 changed files with 0 additions and 8 deletions.
3 changes: 0 additions & 3 deletions docs/en/inference.md
Original file line number Diff line number Diff line change
Expand Up @@ -50,9 +50,6 @@ This command will create a `codes_N` file in the working directory, where N is a
!!! info
For GPUs that do not support bf16, you may need to use the `--half` parameter.

!!! warning
If you are using your own fine-tuned model, please be sure to carry the `--speaker` parameter to ensure the stability of pronunciation.

### 3. Generate vocals from semantic tokens:

#### VQGAN Decoder (not recommended)
Expand Down
3 changes: 0 additions & 3 deletions docs/ja/inference.md
Original file line number Diff line number Diff line change
Expand Up @@ -50,9 +50,6 @@ python tools/llama/generate.py \
!!! info
bf16をサポートしていないGPUの場合、`--half`パラメータを使用する必要があるかもしれません。

!!! warning
自分で微調整したモデルを使用している場合、発音の安定性を確保するために`--speaker`パラメータを必ず持たせてください。

### 3. セマンティックトークンから音声を生成する:

#### VQGANデコーダー(推奨されません)
Expand Down
2 changes: 0 additions & 2 deletions docs/zh/inference.md
Original file line number Diff line number Diff line change
Expand Up @@ -56,8 +56,6 @@ python tools/llama/generate.py \
!!! info
对于不支持 bf16 的 GPU, 你可能需要使用 `--half` 参数.

!!! warning
如果你在使用自己微调的模型, 请务必携带 `--speaker` 参数来保证发音的稳定性.

### 3. 从语义 token 生成人声:

Expand Down

0 comments on commit 3c526c6

Please sign in to comment.