rust/delayed-streams-modeling
1
0
Fork 0
mirror of https://github.com/kyutai-labs/delayed-streams-modeling.git synced 2025-12-23 03:19:57 +00:00
Code Issues Packages Projects Releases Wiki Activity

Address review comments

Browse Source
This commit is contained in:
Václav Volhejn
2025-06-26 16:36:32 +02:00
parent 332f4109c2
commit a55e94a54a
3 changed files with 6 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
configs/config-stt-en-hf.toml
View File

@@ -1,7 +1,7 @@
static_dir = "./static/"
log_dir = "$HOME/tmp/tts-logs"
instance_name = "tts"
authorized_ids = ["open_token"]
authorized_ids = ["public_token"]
[modules.asr]
path = "/api/asr-streaming"

2
configs/config-stt-en_fr-hf.toml
View File

@@ -1,7 +1,7 @@
static_dir = "./static/"
log_dir = "$HOME/tmp/tts-logs"
instance_name = "tts"
authorized_ids = ["open_token"]
authorized_ids = ["public_token"]
[modules.asr]
path = "/api/asr-streaming"

6
scripts/transcribe_from_file_via_rust_server.py
View File

@@ -18,7 +18,6 @@ import websockets
SAMPLE_RATE = 24000
FRAME_SIZE = 1920 # Send data in chunks
HEADERS = {"kyutai-api-key": "open_token"}
def load_and_process_audio(file_path):
@@ -130,4 +129,7 @@ if __name__ == "__main__":
print()
print()
print(transcript)
for word in transcript:
print(
f"{word['timestamp'][0]:7.2f} -{word['timestamp'][1]:7.2f} {word['text']}"
)