dora-distil-whisper 0.3.6__py2.py3-none-any.whl

dora_distil_whisper/__init__.py

@@ -0,0 +1,11 @@
+import os
+
+# Define the path to the README file relative to the package directory
+readme_path = os.path.join(os.path.dirname(os.path.dirname(__file__)), "README.md")
+
+# Read the content of the README file
+try:
+    with open(readme_path, "r", encoding="utf-8") as f:
+        __doc__ = f.read()
+except FileNotFoundError:
+    __doc__ = "README file not found."

dora_distil_whisper/main.py

@@ -0,0 +1,42 @@
+import torch
+from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline
+from dora import Node
+import pyarrow as pa
+import os
+
+os.environ["TRANSFORMERS_OFFLINE"] = "1"
+
+device = "cuda:0" if torch.cuda.is_available() else "cpu"
+torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32
+
+model_id = "distil-whisper/distil-large-v3"
+
+model = AutoModelForSpeechSeq2Seq.from_pretrained(
+    model_id,
+    torch_dtype=torch_dtype,
+    low_cpu_mem_usage=True,
+    use_safetensors=True,
+    local_files_only=True,
+)
+model.to(device)
+
+processor = AutoProcessor.from_pretrained(model_id)
+pipe = pipeline(
+    "automatic-speech-recognition",
+    model=model,
+    tokenizer=processor.tokenizer,
+    feature_extractor=processor.feature_extractor,
+    max_new_tokens=128,
+    torch_dtype=torch_dtype,
+    device=device,
+    generate_kwargs={"language": "chinese"},
+)
+
+
+def main():
+    node = Node()
+    for event in node:
+        if event["type"] == "INPUT":
+            audio = event["value"].to_numpy()
+            result = pipe(audio)
+            node.send_output("text", pa.array([result["text"]]))

dora_distil_whisper-0.3.6.dist-info/METADATA

@@ -0,0 +1,34 @@
+Metadata-Version: 2.1
+Name: dora-distil-whisper
+Version: 0.3.6
+Summary: Dora dora-distil-whisper
+Home-page: https://github.com/dora-rs/dora.git
+License: MIT
+Author: Haixuan Xavier Tao
+Author-email: tao.xavier@outlook.com
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 2
+Classifier: Programming Language :: Python :: 2.7
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.4
+Classifier: Programming Language :: Python :: 3.5
+Classifier: Programming Language :: Python :: 3.6
+Classifier: Programming Language :: Python :: 3.7
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Requires-Dist: accelerate (>=0.29.2,<0.30.0)
+Requires-Dist: dora-rs (>=0.3.6,<0.4.0)
+Requires-Dist: numpy (<2.0.0)
+Requires-Dist: pyarrow (>=5.0.0)
+Requires-Dist: torch (>=2.1.1,<3.0.0)
+Requires-Dist: transformers (>=4.0.0)
+Project-URL: Documentation, https://github.com/dora-rs/dora/blob/main/node-hub/dora-distil-whisper/README.md
+Description-Content-Type: text/markdown
+
+# Dora Node for transforming speech to text (English only)
+
+Check example at [examples/speech-to-text](examples/speech-to-text)
+

dora_distil_whisper-0.3.6.dist-info/RECORD

@@ -0,0 +1,6 @@
+dora_distil_whisper/__init__.py,sha256=Gy4qL4vCeTyA5HR1Yp3ioL4-ClJyW8oi_38CzMuMsBM,358
+dora_distil_whisper/main.py,sha256=xFwK_DhqA-2fWQKPxj6w48NvFVOUvUewcnVd3lnJ0Vc,1123
+dora_distil_whisper-0.3.6.dist-info/METADATA,sha256=gHvOSGNsTHz2djOivsrH59WB-1AE2voM1Nsag10ovlU,1374
+dora_distil_whisper-0.3.6.dist-info/WHEEL,sha256=IrRNNNJ-uuL1ggO5qMvT1GGhQVdQU54d6ZpYqEZfEWo,92
+dora_distil_whisper-0.3.6.dist-info/entry_points.txt,sha256=Q_8wNgkDYxgoKETJjM6ewXWcr_yzRUgsSeBd0uetuRs,69
+dora_distil_whisper-0.3.6.dist-info/RECORD,,

dora_distil_whisper-0.3.6.dist-info/WHEEL

@@ -0,0 +1,4 @@
+Wheel-Version: 1.0
+Generator: poetry-core 1.9.0
+Root-Is-Purelib: true
+Tag: py2.py3-none-any

dora_distil_whisper-0.3.6.dist-info/entry_points.txt

@@ -0,0 +1,3 @@
+[console_scripts]
+dora-distil-whisper=dora_distil_whisper.main:main
+