mirror of
https://github.com/SWivid/F5-TTS.git
synced 2026-07-28 21:35:22 -07:00
update README.md for v1.0.0
This commit is contained in:
@@ -159,9 +159,8 @@ volumes:
|
||||
```bash
|
||||
# Run with flags
|
||||
# Leave --ref_text "" will have ASR model transcribe (extra GPU memory usage)
|
||||
f5-tts_infer-cli \
|
||||
--model "F5-TTS_v1" \
|
||||
--ref_audio "ref_audio.wav" \
|
||||
f5-tts_infer-cli --model F5TTS_v1_Base \
|
||||
--ref_audio "provide_prompt_wav_path_here.wav" \
|
||||
--ref_text "The content, subtitle or transcription of reference audio." \
|
||||
--gen_text "Some text you want TTS model generate for you."
|
||||
|
||||
@@ -182,15 +181,19 @@ f5-tts_infer-cli -c src/f5_tts/infer/examples/multi/story.toml
|
||||
|
||||
## Training
|
||||
|
||||
### 1. Gradio App
|
||||
### 1. With Hugging Face Accelerate
|
||||
|
||||
Read [training & finetuning guidance](src/f5_tts/train) for more instructions.
|
||||
Refer to [training & finetuning guidance](src/f5_tts/train) for best practice.
|
||||
|
||||
### 2. With Gradio App
|
||||
|
||||
```bash
|
||||
# Quick start with Gradio web interface
|
||||
f5-tts_finetune-gradio
|
||||
```
|
||||
|
||||
Read [training & finetuning guidance](src/f5_tts/train) for more instructions.
|
||||
|
||||
|
||||
## [Evaluation](src/f5_tts/eval)
|
||||
|
||||
|
||||
@@ -77,7 +77,7 @@ f5-tts_infer-cli \
|
||||
f5-tts_infer-cli --model F5TTS_Base --vocoder_name bigvgan --load_vocoder_from_local
|
||||
|
||||
# Use custom path checkpoint, e.g.
|
||||
f5-tts_infer-cli --ckpt_file ckpts/F5TTS_Base/model_1200000.safetensors
|
||||
f5-tts_infer-cli --ckpt_file ckpts/F5TTS_v1_Base/model_1250000.safetensors
|
||||
|
||||
# More instructions
|
||||
f5-tts_infer-cli --help
|
||||
|
||||
@@ -40,10 +40,10 @@ Once your datasets are prepared, you can start the training process.
|
||||
accelerate config
|
||||
|
||||
# .yaml files are under src/f5_tts/configs directory
|
||||
accelerate launch src/f5_tts/train/train.py --config-name F5TTS_v1_Base_train.yaml
|
||||
accelerate launch src/f5_tts/train/train.py --config-name F5TTS_v1_Base.yaml
|
||||
|
||||
# possible to overwrite accelerate and hydra config
|
||||
accelerate launch --mixed_precision=fp16 src/f5_tts/train/train.py --config-name F5TTS_v1_Base_train.yaml ++datasets.batch_size_per_gpu=19200
|
||||
accelerate launch --mixed_precision=fp16 src/f5_tts/train/train.py --config-name F5TTS_v1_Base.yaml ++datasets.batch_size_per_gpu=19200
|
||||
```
|
||||
|
||||
### 2. Finetuning practice
|
||||
|
||||
Reference in New Issue
Block a user