Full-text search
18 results
ParthBhuva97 / TTS
model
1 matches
gauri-sharan / speecht5-vector-embeddings
model
1 matches
pyoyoso / Python-Piscine
README.md
model
1 matches
xiaozhongabc / my-speecht5-tts
README.md
model
2 matches
tags:
text-to-speech, tts, speech, en, dataset:Matthijs/cmu-arctic-xvectors, license:mit, region:us
35
36
37
38
39
hijs/cmu-arctic-xvectors", split="validation")
speaker_embeddings = torch.tensor(embeddings_dataset[7306]["xvector"]).unsqueeze(0)
speech = model.generate_speech(inputs["input_ids"], speaker_embeddings, vocoder=vocoder)
fahadqazi / Sindhi-TTS
README.md
model
1 matches
tags:
transformers, tensorboard, safetensors, speecht5, text-to-audio, generated_from_trainer, base_model:fahadqazi/Sindhi-TTS, base_model:finetune:fahadqazi/Sindhi-TTS, license:mit, endpoints_compatible, region:us
53
54
55
56
57
hijs/cmu-arctic-xvectors", split="validation")
speaker_embeddings = embeddings_dataset[7306]["xvector"]
speaker_embeddings = torch.tensor(speaker_embeddings).to(device).unsqueeze(0)
Chan-Y / speecht5_finetuned_tr_commonvoice
README.md
model
1 matches
tags:
transformers, tensorboard, safetensors, speecht5, text-to-audio, generated_from_trainer, tr, base_model:microsoft/speecht5_tts, base_model:finetune:microsoft/speecht5_tts, endpoints_compatible, region:us
35
36
37
38
39
hijs/cmu-arctic-xvectors", split="validation")
speaker_embedding = torch.tensor(embeddings_dataset[7306]["xvector"]).unsqueeze(0)
from transformers import pipeline
pipe = pipeline("text-to-audio", model="Chan-Y/speecht5_finetuned_tr_commonvoice")
blackhole33 / UZBTTS
README.md
model
1 matches
tags:
transformers, tensorboard, safetensors, speecht5, text-to-audio, generated_from_trainer, base_model:microsoft/speecht5_tts, base_model:finetune:microsoft/speecht5_tts, license:mit, endpoints_compatible, region:us
50
51
52
53
54
hijs/cmu-arctic-xvectors", split="validation")
import torch
# voice clone uchun ham ishlatilsa bo'ladi.
speaker_embeddings = torch.tensor(embeddings_dataset[7306]["xvector"]).unsqueeze(0)
Chan-Y / speecht5_tr_commonvoice_2
README.md
model
1 matches
tags:
transformers, tensorboard, safetensors, speecht5, text-to-audio, generated_from_trainer, base_model:microsoft/speecht5_tts, base_model:finetune:microsoft/speecht5_tts, license:mit, endpoints_compatible, region:us
28
29
30
31
32
hijs/cmu-arctic-xvectors", split="validation")
speaker_embedding = torch.tensor(embeddings_dataset[7306]["xvector"]).unsqueeze(0)
from transformers import pipeline
pipe = pipeline("text-to-audio", model="Chan-Y/speecht5_finetuned_tr_commonvoice")
microsoft / speecht5_tts
README.md
model
2 matches
tags:
transformers, pytorch, speecht5, text-to-audio, audio, text-to-speech, dataset:libritts, arxiv:2110.07205, arxiv:1910.09700, license:mit, endpoints_compatible, region:us
70
71
72
73
74
hijs/cmu-arctic-xvectors", split="validation")
speaker_embedding = torch.tensor(embeddings_dataset[7306]["xvector"]).unsqueeze(0)
# You can replace this embedding with your own as well.
speech = synthesiser("Hello, my dog is cooler than you!", forward_params={"speaker_embeddings": speaker_embedding})
GreenCounsel / speecht5_tts_common_voice_5_sv
README.md
model
1 matches
tags:
transformers, pytorch, tensorboard, speecht5, text-to-audio, common_voice, generated_from_trainer, text-to-speech, sv, dataset:mozilla-foundation/common_voice_13_0, license:mit, region:us
59
60
61
62
63
hijs/cmu-arctic-xvectors", split="validation")
speaker_embeddings = torch.tensor(embeddings_dataset[7000]["xvector"]).unsqueeze(0)
set_seed(555)
sobomax / speecht5-rt.post_vocoder.v1
README.md
model
2 matches
tags:
transformers, pytorch, tts, real-time, vocoder, license:bsd-2-clause, endpoints_compatible, region:us
36
37
38
39
40
hijs/cmu-arctic-xvectors` dataset. Such produced reference Mel spectrum were used to feed vocoder and post-vocoder
in chunks. The FFT of generated in "continuous" mode reference waveform was used as a basis for loss-function calculation.
During training, the original vocoder was locked; only our model was trained to mimic the original vocoder as closely as
possible in continuous mode.
DIMITRIOS4 / SummarizeMLPDF
README.md
model
2 matches
Dupaja / speecht5_tts
README.md
model
2 matches
tags:
transformers, pytorch, speecht5, text-to-audio, audio, text-to-speech, dataset:libritts, arxiv:2110.07205, arxiv:1910.09700, license:mit, endpoints_compatible, region:us
70
71
72
73
74
hijs/cmu-arctic-xvectors", split="validation")
speaker_embedding = torch.tensor(embeddings_dataset[7306]["xvector"]).unsqueeze(0)
# You can replace this embedding with your own as well.
speech = synthesiser("Hello, my dog is cooler than you!", forward_params={"speaker_embeddings": speaker_embedding})
RamananR / Ratan_Tata_SpeechT5_Voice_Cloning_Model
README.md
model
1 matches
tags:
speechbrain, ipython, datasets, noisereduce, soundfile, os, torchaudio, torch, transformers, safetensors, ratan, tata, voice-cloning, tts, text-to-speech, en, dataset:RamananR/Ratan_Tata_TTS_Data_English, license:openrail, region:us
63
64
65
66
67
hijs/cmu-arctic-xvectors", split="validation")
speaker_embeddings = torch.tensor(embeddings_dataset[7306]["xvector"]).unsqueeze(0)
# Load the speaker model
spk_model_name = "speechbrain/spkrec-xvect-voxceleb"
gitgato / speech-ts
README.md
model
2 matches
tags:
espnet, speecht5, audio, text-to-speech, dataset:ovieyra21/mabama-v8, dataset:ovieyra21/mabama-v9, arxiv:2110.07205, arxiv:1910.09700, base_model:microsoft/speecht5_tts, base_model:finetune:microsoft/speecht5_tts, license:mit, region:us
78
79
80
81
82
hijs/cmu-arctic-xvectors", split="validation")
speaker_embedding = torch.tensor(embeddings_dataset[7306]["xvector"]).unsqueeze(0)
# You can replace this embedding with your own as well.
speech = synthesiser("Hello, my dog is cooler than you!", forward_params={"speaker_embeddings": speaker_embedding})
seckmaster / microsoft-speecht5_tts
README.md
model
2 matches
tags:
pytorch, speecht5, audio, text-to-speech, dataset:libritts, arxiv:2110.07205, arxiv:1910.09700, license:mit, region:us
70
71
72
73
74
hijs/cmu-arctic-xvectors", split="validation")
speaker_embedding = torch.tensor(embeddings_dataset[7306]["xvector"]).unsqueeze(0)
# You can replace this embedding with your own as well.
speech = synthesiser("Hello, my dog is cooler than you!", forward_params={"speaker_embeddings": speaker_embedding})
pulkitgoel28 / text2speechmodel
README.md
model
2 matches
tags:
pytorch, speecht5, audio, text-to-speech, dataset:libritts, arxiv:2110.07205, arxiv:1910.09700, license:mit, region:us
70
71
72
73
74
hijs/cmu-arctic-xvectors", split="validation")
speaker_embedding = torch.tensor(embeddings_dataset[7306]["xvector"]).unsqueeze(0)
# You can replace this embedding with your own as well.
speech = synthesiser("Hello, my dog is cooler than you!", forward_params={"speaker_embeddings": speaker_embedding})
openpecha / speecht5-tts-01
README.md
model
1 matches
tags:
transformers, pytorch, onnx, safetensors, speecht5, text-to-audio, audio, text-to-speech, dataset:libritts, arxiv:2110.07205, arxiv:1910.09700, license:mit, endpoints_compatible, region:us
102
103
104
105
106
hijs/cmu-arctic-xvectors", split="validation")
speaker_embeddings = torch.tensor(embeddings_dataset[7306]["xvector"]).unsqueeze(0)
speech = model.generate_speech(inputs["input_ids"], speaker_embeddings, vocoder=vocoder)