Inference (Streaming)
Ignore if I am not making sense to you, I want to use xtts-v2. I need to know where I will find these files to download
- config.json [One given in Files and versions?]
- checkpoint [can't find this or this ? tts_models/multilingual/multi-dataset/xtts_v2 [this has config vocab too]]
even if I am correct, please share download links.
import os
import time
import torch
import torchaudio
from TTS.tts.configs.xtts_config import XttsConfig
from TTS.tts.models.xtts import Xtts
print("Loading model...")
config = XttsConfig()
config.load_json("/path/to/xtts/config.json")
model = Xtts.init_from_config(config)
model.load_checkpoint(config, checkpoint_dir="/path/to/xtts/", use_deepspeed=True)
model.cuda()
print("Computing speaker latents...")
gpt_cond_latent, speaker_embedding = model.get_conditioning_latents(audio_path=["reference.wav"])
print("Inference...")
t0 = time.time()
chunks = model.inference_stream(
"It took me quite a long time to develop a voice and now that I have it I am not going to be silent.",
"en",
gpt_cond_latent,
speaker_embedding
)
wav_chuncks = []
for i, chunk in enumerate(chunks):
if i == 0:
print(f"Time to first chunck: {time.time() - t0}")
print(f"Received chunk {i} of audio length {chunk.shape[-1]}")
wav_chuncks.append(chunk)
wav = torch.cat(wav_chuncks, dim=0)
torchaudio.save("xtts_streaming.wav", wav.squeeze().unsqueeze(0).cpu(), 24000)
Found the solution mate?
@Prashant689
the checkpoint is simply this repository,
you can easily download it by doing
import os
import time
import torch
import torchaudio
from TTS.tts.configs.xtts_config import XttsConfig
from TTS.tts.models.xtts import Xtts
from huggingface_hub import snapshot_download
print("Downloading model...")
checkpoint_path = snapshot_download("coqui/XTTS-v2")
config_path = f"{checkpoint_path/config.json"
print("Loading model...")
config = XttsConfig()
config.load_json(config_path )
model = Xtts.init_from_config(config)
model.load_checkpoint(config, checkpoint_dir=checkpoint_path , use_deepspeed=True)
model.cuda()
print("Computing speaker latents...")
gpt_cond_latent, speaker_embedding = model.get_conditioning_latents(audio_path=["reference.wav"])
print("Inference...")
t0 = time.time()
chunks = model.inference_stream(
"It took me quite a long time to develop a voice and now that I have it I am not going to be silent.",
"en",
gpt_cond_latent,
speaker_embedding
)
wav_chuncks = []
for i, chunk in enumerate(chunks):
if i == 0:
print(f"Time to first chunck: {time.time() - t0}")
print(f"Received chunk {i} of audio length {chunk.shape[-1]}")
wav_chuncks.append(chunk)
wav = torch.cat(wav_chuncks, dim=0)
torchaudio.save("xtts_streaming.wav", wav.squeeze().unsqueeze(0).cpu(), 24000)
Facing this error : Streaming inference failed with error: 'StreamGenerationConfig' object has no attribute '_eos_token_tensor'. Can anyone help?