gitea-mirror/F5-TTS
1
0
Fork 0
mirror of https://github.com/SWivid/F5-TTS.git synced 2025-12-12 15:50:07 -08:00
Code Issues Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
SWivid
2025-04-03 15:04:42 +08:00
parent 25b3291715
commit 4b3cd13382
1 changed files with 13 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

26
README.md
View File

@@ -107,6 +107,19 @@ docker container run --rm -it --gpus=all --mount 'type=volume,source=f5-tts,targ
docker container run --rm -it --gpus=all --mount 'type=volume,source=f5-tts,target=/root/.cache/huggingface/hub/' -p 7860:7860 ghcr.io/swivid/f5-tts:main f5-tts_infer-gradio --host 0.0.0.0
```
### Runtime
Deployment solution with Triton and TensorRT-LLM.
#### Benchmark Results
Decoding on a single L20 GPU, using 26 different prompt_audio & target_text pairs.
| Model | Concurrency | Avg Latency | RTF |
|-------|-------------|----------------|-------|
| F5-TTS Base (Vocos) | 1 | 253 ms | 0.0394|
See [detailed instructions](src/f5_tts/runtime/triton_trtllm/README.md) for more information.
## Inference
@@ -179,19 +192,6 @@ f5-tts_infer-cli -c custom.toml
f5-tts_infer-cli -c src/f5_tts/infer/examples/multi/story.toml
```
### 3. Runtime
Deployment solution with Triton and TensorRT-LLM.
#### Benchmark Results
Decoding on a single L20 GPU, using 26 different prompt_audio & target_text pairs.
| Model | Concurrency | Avg Latency | RTF |
|-------|-------------|----------------|-------|
| F5-TTS Base (Vocos) | 1 | 253 ms | 0.0394|
See [detailed instructions](src/f5_tts/runtime/triton_trtllm/README.md) for more information.
## Training