jonmac303 commited on
Commit
d39299f
·
1 Parent(s): 859b546

Add Chatterbox Turbo HF wrapper

Browse files
Files changed (6) hide show
  1. .DS_Store +0 -0
  2. README.md +16 -0
  3. __init__.py.txt +7 -0
  4. config.json +4 -0
  5. pipeline.py.txt +14 -0
  6. requirements.txt +5 -0
.DS_Store ADDED
Binary file (6.15 kB). View file
 
README.md ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ pipeline_tag: text-to-speech
3
+ license: apache-2.0
4
+ ---
5
+
6
+ # Chatterbox Turbo (HF Wrapper)
7
+
8
+ This repository wraps ResembleAI Chatterbox Turbo in a
9
+ Transformers-compatible text-to-speech pipeline.
10
+
11
+ ## Usage
12
+
13
+ Input: text
14
+ Output: audio waveform
15
+
16
+ Supports zero-shot voice cloning via voice embeddings.
__init__.py.txt ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ from transformers import PIPELINE_REGISTRY
2
+ from .pipeline import ChatterboxTurboPipeline
3
+
4
+ PIPELINE_REGISTRY.register_pipeline(
5
+ "text-to-speech",
6
+ pipeline_class=ChatterboxTurboPipeline
7
+ )
config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "model_type": "chatterbox-turbo",
3
+ "architectures": ["ChatterboxTurboPipeline"]
4
+ }
pipeline.py.txt ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ from transformers import Pipeline
2
+ from chatterbox.turbo import synthesize_turbo
3
+
4
+ class ChatterboxTurboPipeline(Pipeline):
5
+ def _sanitize_parameters(self, **kwargs):
6
+ return {}, {}, kwargs
7
+
8
+ def __call__(self, text, voice_embedding=None, **kwargs):
9
+ audio = synthesize_turbo(
10
+ text=text,
11
+ voice_embedding=voice_embedding,
12
+ **kwargs
13
+ )
14
+ return audio
requirements.txt ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ torch
2
+ transformers
3
+ soundfile
4
+ numpy
5
+ git+https://github.com/resemble-ai/chatterbox.git