Medix-AI/coqui-tts
Medix-AI
/
coqui-tts
mirror of https://github.com/coqui-ai/TTS.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

update docs

This commit is contained in:
WeberJulian 2023-11-08 10:16:36 +01:00
parent 5c81500e3e
commit ea56ec041f
1 changed files with 3 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
docs/source/models/xtts.md
View File

@ -115,7 +115,7 @@ model.load_checkpoint(config, checkpoint_dir="/path/to/xtts/", use_deepspeed=Tru
model.cuda() model.cuda()
print("Computing speaker latents...") print("Computing speaker latents...")
gpt_cond_latent, diffusion_conditioning, speaker_embedding = model.get_conditioning_latents(audio_path=["reference.wav"]) gpt_cond_latent, speaker_embedding = model.get_conditioning_latents(audio_path=["reference.wav"])
print("Inference...") print("Inference...")
out = model.inference( out = model.inference(
@ -123,7 +123,6 @@ out = model.inference(
"en", "en",
gpt_cond_latent, gpt_cond_latent,
speaker_embedding, speaker_embedding,
diffusion_conditioning,
temperature=0.7, # Add custom parameters here temperature=0.7, # Add custom parameters here
) )
torchaudio.save("xtts.wav", torch.tensor(out["wav"]).unsqueeze(0), 24000) torchaudio.save("xtts.wav", torch.tensor(out["wav"]).unsqueeze(0), 24000)
@ -152,7 +151,7 @@ model.load_checkpoint(config, checkpoint_dir="/path/to/xtts/", use_deepspeed=Tru
model.cuda() model.cuda()
print("Computing speaker latents...") print("Computing speaker latents...")
gpt_cond_latent, _, speaker_embedding = model.get_conditioning_latents(audio_path=["reference.wav"]) gpt_cond_latent, speaker_embedding = model.get_conditioning_latents(audio_path=["reference.wav"])
print("Inference...") print("Inference...")
t0 = time.time() t0 = time.time()
@ -209,7 +208,7 @@ model.load_checkpoint(config, checkpoint_path=XTTS_CHECKPOINT, vocab_path=TOKENI
model.cuda() model.cuda()
print("Computing speaker latents...") print("Computing speaker latents...")
gpt_cond_latent, diffusion_conditioning, speaker_embedding = model.get_conditioning_latents(audio_path=[SPEAKER_REFERENCE]) gpt_cond_latent, speaker_embedding = model.get_conditioning_latents(audio_path=[SPEAKER_REFERENCE])
print("Inference...") print("Inference...")
out = model.inference( out = model.inference(
@ -217,7 +216,6 @@ out = model.inference(
"en", "en",
gpt_cond_latent, gpt_cond_latent,
speaker_embedding, speaker_embedding,
diffusion_conditioning,
temperature=0.7, # Add custom parameters here temperature=0.7, # Add custom parameters here
) )
torchaudio.save(OUTPUT_WAV_PATH, torch.tensor(out["wav"]).unsqueeze(0), 24000) torchaudio.save(OUTPUT_WAV_PATH, torch.tensor(out["wav"]).unsqueeze(0), 24000)