update README.md for v1.0.0

This commit is contained in:
SWivid
2025-03-12 17:39:30 +08:00
parent ca6e49adaa
commit bf651d541e
3 changed files with 11 additions and 8 deletions
+8 -5
View File
@@ -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)
+1 -1
View File
@@ -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
+2 -2
View File
@@ -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