Commit @a3f23eca8b697c3c5a6767f969e6d007b755acd3 - yjyoon/whisper_server

Fedir Zadniprovskyi 01-10

chore: misc changes

@a3f23eca8b697c3c5a6767f969e6d007b755acd3

e827e03

a3f23ec

Dockerfile

--- Dockerfile

+++ Dockerfile


 COPY --chown=ubuntu --from=ghcr.io/astral-sh/uv:0.5.14 /uv /bin/uv
 # https://docs.astral.sh/uv/guides/integration/docker/#intermediate-layers
 # https://docs.astral.sh/uv/guides/integration/docker/#compiling-bytecode
+# TODO: figure out if `/home/ubuntu/.cache/uv` should be used instead of `/root/.cache/uv`
 RUN --mount=type=cache,target=/root/.cache/uv \
     --mount=type=bind,source=uv.lock,target=uv.lock \
     --mount=type=bind,source=pyproject.toml,target=pyproject.toml \

e827e03

a3f23ec

compose.yaml

--- compose.yaml

+++ compose.yaml


     restart: unless-stopped
     ports:
       - 8000:8000
-    develop:
-      watch:
-        - path: faster_whisper_server
-          action: rebuild

e827e03

a3f23ec

docs/installation.md

--- docs/installation.md

+++ docs/installation.md


 === "CUDA"
 
     ```bash
-    docker run --rm --detach --publish 8000:8000 --name faster-whisper-server --volume hf-hub-cache:/home/ubuntu/.cache/huggingface/hub --gpus=all fedirz/faster-whisper-server:latest-cuda
+    docker run \
+      --rm \
+      --detach \
+      --publish 8000:8000 \
+      --name faster-whisper-server \
+      --volume hf-hub-cache:/home/ubuntu/.cache/huggingface/hub \
+      --gpus=all \
+      fedirz/faster-whisper-server:latest-cuda
     ```
 
 === "CUDA (with CDI feature enabled)"
 
     ```bash
-    docker run --rm --detach --publish 8000:8000 --name faster-whisper-server --volume hf-hub-cache:/home/ubuntu/.cache/huggingface/hub --device=nvidia.com/gpu=all fedirz/faster-whisper-server:latest-cuda
+    docker run \
+      --rm \
+      --detach \
+      --publish 8000:8000 \
+      --name faster-whisper-server \
+      --volume hf-hub-cache:/home/ubuntu/.cache/huggingface/hub \
+      --device=nvidia.com/gpu=all \
+      fedirz/faster-whisper-server:latest-cuda
     ```
 
 === "CPU"
 
     ```bash
-    docker run --rm --detach --publish 8000:8000 --name faster-whisper-server --volume hf-hub-cache:/home/ubuntu/.cache/huggingface/hub fedirz/faster-whisper-server:latest-cpu
+    docker run \
+      --rm \
+      --detach \
+      --publish 8000:8000 \
+      --name faster-whisper-server \
+      --volume hf-hub-cache:/home/ubuntu/.cache/huggingface/hub \
+      fedirz/faster-whisper-server:latest-cpu
     ```
 
 ## Kubernetes
+
 WARNING: it was written few months ago and may be outdated.
 Please refer to this [blog post](https://substratus.ai/blog/deploying-faster-whisper-on-k8s)
 
-## Python (requires Python 3.12+)
+## Python (requires Python 3.12+ and `uv` package manager)
 
 ```bash
 git clone https://github.com/fedirz/faster-whisper-server.git

Add a comment

Open 0
Closed 0

List

...	...	@@ -19,6 +19,7 @@
19	19	COPY --chown=ubuntu --from=ghcr.io/astral-sh/uv:0.5.14 /uv /bin/uv
20	20	# https://docs.astral.sh/uv/guides/integration/docker/#intermediate-layers
21	21	# https://docs.astral.sh/uv/guides/integration/docker/#compiling-bytecode
	22	+# TODO: figure out if `/home/ubuntu/.cache/uv` should be used instead of `/root/.cache/uv`
22	23	RUN --mount=type=cache,target=/root/.cache/uv \
23	24	--mount=type=bind,source=uv.lock,target=uv.lock \
24	25	--mount=type=bind,source=pyproject.toml,target=pyproject.toml \

...	...	@@ -70,26 +70,47 @@
70	70	=== "CUDA"
71	71
72	72	```bash
73		- docker run --rm --detach --publish 8000:8000 --name faster-whisper-server --volume hf-hub-cache:/home/ubuntu/.cache/huggingface/hub --gpus=all fedirz/faster-whisper-server:latest-cuda
	73	+ docker run \
	74	+ --rm \
	75	+ --detach \
	76	+ --publish 8000:8000 \
	77	+ --name faster-whisper-server \
	78	+ --volume hf-hub-cache:/home/ubuntu/.cache/huggingface/hub \
	79	+ --gpus=all \
	80	+ fedirz/faster-whisper-server:latest-cuda
74	81	```
75	82
76	83	=== "CUDA (with CDI feature enabled)"
77	84
78	85	```bash
79		- docker run --rm --detach --publish 8000:8000 --name faster-whisper-server --volume hf-hub-cache:/home/ubuntu/.cache/huggingface/hub --device=nvidia.com/gpu=all fedirz/faster-whisper-server:latest-cuda
	86	+ docker run \
	87	+ --rm \
	88	+ --detach \
	89	+ --publish 8000:8000 \
	90	+ --name faster-whisper-server \
	91	+ --volume hf-hub-cache:/home/ubuntu/.cache/huggingface/hub \
	92	+ --device=nvidia.com/gpu=all \
	93	+ fedirz/faster-whisper-server:latest-cuda
80	94	```
81	95
82	96	=== "CPU"
83	97
84	98	```bash
85		- docker run --rm --detach --publish 8000:8000 --name faster-whisper-server --volume hf-hub-cache:/home/ubuntu/.cache/huggingface/hub fedirz/faster-whisper-server:latest-cpu
	99	+ docker run \
	100	+ --rm \
	101	+ --detach \
	102	+ --publish 8000:8000 \
	103	+ --name faster-whisper-server \
	104	+ --volume hf-hub-cache:/home/ubuntu/.cache/huggingface/hub \
	105	+ fedirz/faster-whisper-server:latest-cpu
86	106	```
87	107
88	108	## Kubernetes
	109	+
89	110	WARNING: it was written few months ago and may be outdated.
90	111	Please refer to this [blog post](https://substratus.ai/blog/deploying-faster-whisper-on-k8s)
91	112
92		-## Python (requires Python 3.12+)
	113	+## Python (requires Python 3.12+ and `uv` package manager)
93	114
94	115	```bash
95	116	git clone https://github.com/fedirz/faster-whisper-server.git

...	...	@@ -11,7 +11,3 @@
11	11	restart: unless-stopped
12	12	ports:
13	13	- 8000:8000
14		- develop:
15		- watch:
16		- - path: faster_whisper_server
17		- action: rebuild

Delete comment