Spaces:
Runtime error
Runtime error
Commit
Β·
b6843d1
1
Parent(s):
78c3bd0
rename to chatterbox
Browse filesThis view is limited to 50 files because it contains too many changes. Β
See raw diff
- chatterbox/src/chatterbox/__init__.py +1 -0
- {orator/src/orator β chatterbox/src/chatterbox}/models/s3gen/__init__.py +0 -0
- {orator/src/orator β chatterbox/src/chatterbox}/models/s3gen/const.py +0 -0
- {orator/src/orator β chatterbox/src/chatterbox}/models/s3gen/decoder.py +0 -0
- {orator/src/orator β chatterbox/src/chatterbox}/models/s3gen/f0_predictor.py +0 -0
- {orator/src/orator β chatterbox/src/chatterbox}/models/s3gen/flow.py +0 -0
- {orator/src/orator β chatterbox/src/chatterbox}/models/s3gen/flow_matching.py +0 -0
- {orator/src/orator β chatterbox/src/chatterbox}/models/s3gen/hifigan.py +0 -0
- {orator/src/orator β chatterbox/src/chatterbox}/models/s3gen/matcha/decoder.py +0 -0
- {orator/src/orator β chatterbox/src/chatterbox}/models/s3gen/matcha/flow_matching.py +0 -0
- {orator/src/orator β chatterbox/src/chatterbox}/models/s3gen/matcha/text_encoder.py +0 -0
- {orator/src/orator β chatterbox/src/chatterbox}/models/s3gen/matcha/transformer.py +0 -0
- {orator/src/orator β chatterbox/src/chatterbox}/models/s3gen/s3gen.py +0 -0
- {orator/src/orator β chatterbox/src/chatterbox}/models/s3gen/transformer/__init__.py +0 -0
- {orator/src/orator β chatterbox/src/chatterbox}/models/s3gen/transformer/activation.py +0 -0
- {orator/src/orator β chatterbox/src/chatterbox}/models/s3gen/transformer/attention.py +0 -0
- {orator/src/orator β chatterbox/src/chatterbox}/models/s3gen/transformer/convolution.py +0 -0
- {orator/src/orator β chatterbox/src/chatterbox}/models/s3gen/transformer/embedding.py +0 -0
- {orator/src/orator β chatterbox/src/chatterbox}/models/s3gen/transformer/encoder_layer.py +0 -0
- {orator/src/orator β chatterbox/src/chatterbox}/models/s3gen/transformer/positionwise_feed_forward.py +0 -0
- {orator/src/orator β chatterbox/src/chatterbox}/models/s3gen/transformer/subsampling.py +0 -0
- {orator/src/orator β chatterbox/src/chatterbox}/models/s3gen/transformer/upsample_encoder.py +0 -0
- {orator/src/orator β chatterbox/src/chatterbox}/models/s3gen/utils/class_utils.py +0 -0
- {orator/src/orator β chatterbox/src/chatterbox}/models/s3gen/utils/mask.py +0 -0
- {orator/src/orator β chatterbox/src/chatterbox}/models/s3gen/utils/mel.py +0 -0
- {orator/src/orator β chatterbox/src/chatterbox}/models/s3gen/xvector.py +0 -0
- {orator/src/orator β chatterbox/src/chatterbox}/models/s3tokenizer/__init__.py +0 -0
- {orator/src/orator β chatterbox/src/chatterbox}/models/s3tokenizer/s3tokenizer.py +0 -0
- {orator/src/orator β chatterbox/src/chatterbox}/models/t3/__init__.py +0 -0
- {orator/src/orator β chatterbox/src/chatterbox}/models/t3/inference/alignment_stream_analyzer.py +0 -0
- {orator/src/orator β chatterbox/src/chatterbox}/models/t3/inference/t3_hf_backend.py +0 -0
- {orator/src/orator β chatterbox/src/chatterbox}/models/t3/llama_configs.py +0 -0
- {orator/src/orator β chatterbox/src/chatterbox}/models/t3/modules/cond_enc.py +0 -0
- {orator/src/orator β chatterbox/src/chatterbox}/models/t3/modules/learned_pos_emb.py +0 -0
- {orator/src/orator β chatterbox/src/chatterbox}/models/t3/modules/perceiver.py +0 -0
- {orator/src/orator β chatterbox/src/chatterbox}/models/t3/modules/t3_config.py +0 -0
- {orator/src/orator β chatterbox/src/chatterbox}/models/t3/t3.py +0 -0
- {orator/src/orator β chatterbox/src/chatterbox}/models/tokenizers/__init__.py +0 -0
- {orator/src/orator β chatterbox/src/chatterbox}/models/tokenizers/tokenizer.py +0 -0
- {orator/src/orator β chatterbox/src/chatterbox}/models/voice_encoder/__init__.py +0 -0
- {orator/src/orator β chatterbox/src/chatterbox}/models/voice_encoder/config.py +0 -0
- {orator/src/orator β chatterbox/src/chatterbox}/models/voice_encoder/melspec.py +0 -0
- {orator/src/orator β chatterbox/src/chatterbox}/models/voice_encoder/voice_encoder.py +0 -0
- {orator/src/orator β chatterbox/src/chatterbox}/tts.py +4 -4
- {orator/src/orator β chatterbox/src/chatterbox}/vc.py +4 -4
- orator/src/orator.egg-info/PKG-INFO +0 -17
- orator/src/orator.egg-info/SOURCES.txt +0 -52
- orator/src/orator.egg-info/dependency_links.txt +0 -1
- orator/src/orator.egg-info/requires.txt +0 -10
- orator/src/orator.egg-info/top_level.txt +0 -1
chatterbox/src/chatterbox/__init__.py
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
from .tts import ChatterboxTTS
|
{orator/src/orator β chatterbox/src/chatterbox}/models/s3gen/__init__.py
RENAMED
File without changes
|
{orator/src/orator β chatterbox/src/chatterbox}/models/s3gen/const.py
RENAMED
File without changes
|
{orator/src/orator β chatterbox/src/chatterbox}/models/s3gen/decoder.py
RENAMED
File without changes
|
{orator/src/orator β chatterbox/src/chatterbox}/models/s3gen/f0_predictor.py
RENAMED
File without changes
|
{orator/src/orator β chatterbox/src/chatterbox}/models/s3gen/flow.py
RENAMED
File without changes
|
{orator/src/orator β chatterbox/src/chatterbox}/models/s3gen/flow_matching.py
RENAMED
File without changes
|
{orator/src/orator β chatterbox/src/chatterbox}/models/s3gen/hifigan.py
RENAMED
File without changes
|
{orator/src/orator β chatterbox/src/chatterbox}/models/s3gen/matcha/decoder.py
RENAMED
File without changes
|
{orator/src/orator β chatterbox/src/chatterbox}/models/s3gen/matcha/flow_matching.py
RENAMED
File without changes
|
{orator/src/orator β chatterbox/src/chatterbox}/models/s3gen/matcha/text_encoder.py
RENAMED
File without changes
|
{orator/src/orator β chatterbox/src/chatterbox}/models/s3gen/matcha/transformer.py
RENAMED
File without changes
|
{orator/src/orator β chatterbox/src/chatterbox}/models/s3gen/s3gen.py
RENAMED
File without changes
|
{orator/src/orator β chatterbox/src/chatterbox}/models/s3gen/transformer/__init__.py
RENAMED
File without changes
|
{orator/src/orator β chatterbox/src/chatterbox}/models/s3gen/transformer/activation.py
RENAMED
File without changes
|
{orator/src/orator β chatterbox/src/chatterbox}/models/s3gen/transformer/attention.py
RENAMED
File without changes
|
{orator/src/orator β chatterbox/src/chatterbox}/models/s3gen/transformer/convolution.py
RENAMED
File without changes
|
{orator/src/orator β chatterbox/src/chatterbox}/models/s3gen/transformer/embedding.py
RENAMED
File without changes
|
{orator/src/orator β chatterbox/src/chatterbox}/models/s3gen/transformer/encoder_layer.py
RENAMED
File without changes
|
{orator/src/orator β chatterbox/src/chatterbox}/models/s3gen/transformer/positionwise_feed_forward.py
RENAMED
File without changes
|
{orator/src/orator β chatterbox/src/chatterbox}/models/s3gen/transformer/subsampling.py
RENAMED
File without changes
|
{orator/src/orator β chatterbox/src/chatterbox}/models/s3gen/transformer/upsample_encoder.py
RENAMED
File without changes
|
{orator/src/orator β chatterbox/src/chatterbox}/models/s3gen/utils/class_utils.py
RENAMED
File without changes
|
{orator/src/orator β chatterbox/src/chatterbox}/models/s3gen/utils/mask.py
RENAMED
File without changes
|
{orator/src/orator β chatterbox/src/chatterbox}/models/s3gen/utils/mel.py
RENAMED
File without changes
|
{orator/src/orator β chatterbox/src/chatterbox}/models/s3gen/xvector.py
RENAMED
File without changes
|
{orator/src/orator β chatterbox/src/chatterbox}/models/s3tokenizer/__init__.py
RENAMED
File without changes
|
{orator/src/orator β chatterbox/src/chatterbox}/models/s3tokenizer/s3tokenizer.py
RENAMED
File without changes
|
{orator/src/orator β chatterbox/src/chatterbox}/models/t3/__init__.py
RENAMED
File without changes
|
{orator/src/orator β chatterbox/src/chatterbox}/models/t3/inference/alignment_stream_analyzer.py
RENAMED
File without changes
|
{orator/src/orator β chatterbox/src/chatterbox}/models/t3/inference/t3_hf_backend.py
RENAMED
File without changes
|
{orator/src/orator β chatterbox/src/chatterbox}/models/t3/llama_configs.py
RENAMED
File without changes
|
{orator/src/orator β chatterbox/src/chatterbox}/models/t3/modules/cond_enc.py
RENAMED
File without changes
|
{orator/src/orator β chatterbox/src/chatterbox}/models/t3/modules/learned_pos_emb.py
RENAMED
File without changes
|
{orator/src/orator β chatterbox/src/chatterbox}/models/t3/modules/perceiver.py
RENAMED
File without changes
|
{orator/src/orator β chatterbox/src/chatterbox}/models/t3/modules/t3_config.py
RENAMED
File without changes
|
{orator/src/orator β chatterbox/src/chatterbox}/models/t3/t3.py
RENAMED
File without changes
|
{orator/src/orator β chatterbox/src/chatterbox}/models/tokenizers/__init__.py
RENAMED
File without changes
|
{orator/src/orator β chatterbox/src/chatterbox}/models/tokenizers/tokenizer.py
RENAMED
File without changes
|
{orator/src/orator β chatterbox/src/chatterbox}/models/voice_encoder/__init__.py
RENAMED
File without changes
|
{orator/src/orator β chatterbox/src/chatterbox}/models/voice_encoder/config.py
RENAMED
File without changes
|
{orator/src/orator β chatterbox/src/chatterbox}/models/voice_encoder/melspec.py
RENAMED
File without changes
|
{orator/src/orator β chatterbox/src/chatterbox}/models/voice_encoder/voice_encoder.py
RENAMED
File without changes
|
{orator/src/orator β chatterbox/src/chatterbox}/tts.py
RENAMED
@@ -14,7 +14,7 @@ from .models.voice_encoder import VoiceEncoder
|
|
14 |
from .models.t3.modules.cond_enc import T3Cond
|
15 |
|
16 |
|
17 |
-
REPO_ID = "ResembleAI/
|
18 |
|
19 |
|
20 |
def change_pace(speech_tokens: torch.Tensor, pace: float):
|
@@ -68,7 +68,7 @@ class Conditionals:
|
|
68 |
return cls(T3Cond(**kwargs['t3']), kwargs['gen'])
|
69 |
|
70 |
|
71 |
-
class
|
72 |
ENC_COND_LEN = 6 * S3_SR
|
73 |
DEC_COND_LEN = 10 * S3GEN_SR
|
74 |
|
@@ -90,7 +90,7 @@ class OratorTTS:
|
|
90 |
self.conds = conds
|
91 |
|
92 |
@classmethod
|
93 |
-
def from_local(cls, ckpt_dir, device) -> '
|
94 |
ckpt_dir = Path(ckpt_dir)
|
95 |
|
96 |
ve = VoiceEncoder()
|
@@ -122,7 +122,7 @@ class OratorTTS:
|
|
122 |
return cls(t3, s3gen, ve, tokenizer, device, conds=conds)
|
123 |
|
124 |
@classmethod
|
125 |
-
def from_pretrained(cls, device) -> '
|
126 |
for fpath in ["ve.pt", "t3.pt", "s3gen.pt", "tokenizer.json", "conds.pt"]:
|
127 |
local_path = hf_hub_download(repo_id=REPO_ID, filename=fpath)
|
128 |
|
|
|
14 |
from .models.t3.modules.cond_enc import T3Cond
|
15 |
|
16 |
|
17 |
+
REPO_ID = "ResembleAI/chatterbox"
|
18 |
|
19 |
|
20 |
def change_pace(speech_tokens: torch.Tensor, pace: float):
|
|
|
68 |
return cls(T3Cond(**kwargs['t3']), kwargs['gen'])
|
69 |
|
70 |
|
71 |
+
class ChatterboxTTS:
|
72 |
ENC_COND_LEN = 6 * S3_SR
|
73 |
DEC_COND_LEN = 10 * S3GEN_SR
|
74 |
|
|
|
90 |
self.conds = conds
|
91 |
|
92 |
@classmethod
|
93 |
+
def from_local(cls, ckpt_dir, device) -> 'ChatterboxTTS':
|
94 |
ckpt_dir = Path(ckpt_dir)
|
95 |
|
96 |
ve = VoiceEncoder()
|
|
|
122 |
return cls(t3, s3gen, ve, tokenizer, device, conds=conds)
|
123 |
|
124 |
@classmethod
|
125 |
+
def from_pretrained(cls, device) -> 'ChatterboxTTS':
|
126 |
for fpath in ["ve.pt", "t3.pt", "s3gen.pt", "tokenizer.json", "conds.pt"]:
|
127 |
local_path = hf_hub_download(repo_id=REPO_ID, filename=fpath)
|
128 |
|
{orator/src/orator β chatterbox/src/chatterbox}/vc.py
RENAMED
@@ -8,10 +8,10 @@ from .models.s3tokenizer import S3_SR
|
|
8 |
from .models.s3gen import S3GEN_SR, S3Gen
|
9 |
|
10 |
|
11 |
-
REPO_ID = "ResembleAI/
|
12 |
|
13 |
|
14 |
-
class
|
15 |
ENC_COND_LEN = 6 * S3_SR
|
16 |
DEC_COND_LEN = 10 * S3GEN_SR
|
17 |
|
@@ -33,7 +33,7 @@ class OratorVC:
|
|
33 |
}
|
34 |
|
35 |
@classmethod
|
36 |
-
def from_local(cls, ckpt_dir, device) -> '
|
37 |
ckpt_dir = Path(ckpt_dir)
|
38 |
ref_dict = None
|
39 |
if (builtin_voice := ckpt_dir / "conds.pt").exists():
|
@@ -49,7 +49,7 @@ class OratorVC:
|
|
49 |
return cls(s3gen, device, ref_dict=ref_dict)
|
50 |
|
51 |
@classmethod
|
52 |
-
def from_pretrained(cls, device) -> '
|
53 |
for fpath in ["s3gen.pt", "conds.pt"]:
|
54 |
local_path = hf_hub_download(repo_id=REPO_ID, filename=fpath)
|
55 |
|
|
|
8 |
from .models.s3gen import S3GEN_SR, S3Gen
|
9 |
|
10 |
|
11 |
+
REPO_ID = "ResembleAI/chatterbox"
|
12 |
|
13 |
|
14 |
+
class ChatterboxVC:
|
15 |
ENC_COND_LEN = 6 * S3_SR
|
16 |
DEC_COND_LEN = 10 * S3GEN_SR
|
17 |
|
|
|
33 |
}
|
34 |
|
35 |
@classmethod
|
36 |
+
def from_local(cls, ckpt_dir, device) -> 'ChatterboxVC':
|
37 |
ckpt_dir = Path(ckpt_dir)
|
38 |
ref_dict = None
|
39 |
if (builtin_voice := ckpt_dir / "conds.pt").exists():
|
|
|
49 |
return cls(s3gen, device, ref_dict=ref_dict)
|
50 |
|
51 |
@classmethod
|
52 |
+
def from_pretrained(cls, device) -> 'ChatterboxVC':
|
53 |
for fpath in ["s3gen.pt", "conds.pt"]:
|
54 |
local_path = hf_hub_download(repo_id=REPO_ID, filename=fpath)
|
55 |
|
orator/src/orator.egg-info/PKG-INFO
DELETED
@@ -1,17 +0,0 @@
|
|
1 |
-
Metadata-Version: 2.4
|
2 |
-
Name: orator
|
3 |
-
Version: 0.1
|
4 |
-
Description-Content-Type: text/markdown
|
5 |
-
Requires-Dist: numpy==1.26.0
|
6 |
-
Requires-Dist: resampy==0.4.3
|
7 |
-
Requires-Dist: librosa==0.10.0
|
8 |
-
Requires-Dist: s3tokenizer
|
9 |
-
Requires-Dist: torch==2.6.0
|
10 |
-
Requires-Dist: torchaudio==2.6.0
|
11 |
-
Requires-Dist: transformers==4.46.3
|
12 |
-
Requires-Dist: diffusers==0.29.0
|
13 |
-
Requires-Dist: omegaconf==2.3.0
|
14 |
-
Requires-Dist: conformer==0.3.2
|
15 |
-
|
16 |
-
# orator
|
17 |
-
Open source TTS model
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
orator/src/orator.egg-info/SOURCES.txt
DELETED
@@ -1,52 +0,0 @@
|
|
1 |
-
README.md
|
2 |
-
pyproject.toml
|
3 |
-
src/orator/__init__.py
|
4 |
-
src/orator/model_checkpoints.py
|
5 |
-
src/orator/tts.py
|
6 |
-
src/orator.egg-info/PKG-INFO
|
7 |
-
src/orator.egg-info/SOURCES.txt
|
8 |
-
src/orator.egg-info/dependency_links.txt
|
9 |
-
src/orator.egg-info/requires.txt
|
10 |
-
src/orator.egg-info/top_level.txt
|
11 |
-
src/orator/models/s3gen/__init__.py
|
12 |
-
src/orator/models/s3gen/const.py
|
13 |
-
src/orator/models/s3gen/decoder.py
|
14 |
-
src/orator/models/s3gen/f0_predictor.py
|
15 |
-
src/orator/models/s3gen/flow.py
|
16 |
-
src/orator/models/s3gen/flow_matching.py
|
17 |
-
src/orator/models/s3gen/hifigan.py
|
18 |
-
src/orator/models/s3gen/s3gen.py
|
19 |
-
src/orator/models/s3gen/xvector.py
|
20 |
-
src/orator/models/s3gen/matcha/decoder.py
|
21 |
-
src/orator/models/s3gen/matcha/flow_matching.py
|
22 |
-
src/orator/models/s3gen/matcha/text_encoder.py
|
23 |
-
src/orator/models/s3gen/matcha/transformer.py
|
24 |
-
src/orator/models/s3gen/transformer/__init__.py
|
25 |
-
src/orator/models/s3gen/transformer/activation.py
|
26 |
-
src/orator/models/s3gen/transformer/attention.py
|
27 |
-
src/orator/models/s3gen/transformer/convolution.py
|
28 |
-
src/orator/models/s3gen/transformer/embedding.py
|
29 |
-
src/orator/models/s3gen/transformer/encoder_layer.py
|
30 |
-
src/orator/models/s3gen/transformer/positionwise_feed_forward.py
|
31 |
-
src/orator/models/s3gen/transformer/subsampling.py
|
32 |
-
src/orator/models/s3gen/transformer/upsample_encoder.py
|
33 |
-
src/orator/models/s3gen/utils/class_utils.py
|
34 |
-
src/orator/models/s3gen/utils/mask.py
|
35 |
-
src/orator/models/s3gen/utils/mel.py
|
36 |
-
src/orator/models/s3tokenizer/__init__.py
|
37 |
-
src/orator/models/s3tokenizer/s3tokenizer.py
|
38 |
-
src/orator/models/t3/__init__.py
|
39 |
-
src/orator/models/t3/llama_configs.py
|
40 |
-
src/orator/models/t3/t3.py
|
41 |
-
src/orator/models/t3/inference/t3_hf_backend.py
|
42 |
-
src/orator/models/t3/modules/cond_enc.py
|
43 |
-
src/orator/models/t3/modules/learned_pos_emb.py
|
44 |
-
src/orator/models/t3/modules/perceiver.py
|
45 |
-
src/orator/models/t3/modules/t3_config.py
|
46 |
-
src/orator/models/tokenizers/__init__.py
|
47 |
-
src/orator/models/tokenizers/tokenizer.py
|
48 |
-
src/orator/models/voice_encoder/__init__.py
|
49 |
-
src/orator/models/voice_encoder/voice_encoder.py
|
50 |
-
src/orator/transforms/spectrogram.py
|
51 |
-
src/orator/transforms/syn_transforms.py
|
52 |
-
src/orator/transforms/webrtc.py
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
orator/src/orator.egg-info/dependency_links.txt
DELETED
@@ -1 +0,0 @@
|
|
1 |
-
|
|
|
|
orator/src/orator.egg-info/requires.txt
DELETED
@@ -1,10 +0,0 @@
|
|
1 |
-
numpy==1.26.0
|
2 |
-
resampy==0.4.3
|
3 |
-
librosa==0.10.0
|
4 |
-
s3tokenizer
|
5 |
-
torch==2.6.0
|
6 |
-
torchaudio==2.6.0
|
7 |
-
transformers==4.46.3
|
8 |
-
diffusers==0.29.0
|
9 |
-
omegaconf==2.3.0
|
10 |
-
conformer==0.3.2
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
orator/src/orator.egg-info/top_level.txt
DELETED
@@ -1 +0,0 @@
|
|
1 |
-
orator
|
|
|
|